Will Seeing Machines licence its software stack for humanoid development?

What I’m about to discuss might seem a little ‘out-there’ to some, but I think it merits consideration by investors keen to catch one of the next big investment opportunities that Seeing Machines could play a major role in.

In a recent broker note from Morgan Stanley, entitled Humanoid Tech – Grasping the Future, its analysts wrote: “Building physical AI takes a tremendous amount of semiconductor resource, and most of the value sits in (1) the AI brain technology, (2) AI vision and (3) analog chips for sensing. Companies providing these enabling technologies stand to benefit as much as the humanoids makers themselves, where most of the value creation lies with distribution. We argue that understanding which capabilities are advancing fastest, ecosystem readiness and realistic adoption timelines will dictate commercial traction.”

I asked the AI Deep Seek this question: Is Seeing Machines technology of possible use in the areas 1-3 where semiconductors are used in humanoids?

Its reply was fascinating:

Excellent question. Let’s break down Morgan Stanley’s framework and evaluate how Seeing Machines’ technology aligns with it.

First, a quick recap of the Morgan Stanley note’s three key semiconductor-intensive areas for physical AI/humanoids:

1.  The AI Brain Technology: The central AI compute (e.g., high-performance SoCs, GPUs, NPUs) for perception, decision-making, and motor control.

2.  AI Vision: Sensors (cameras, LiDAR, radar) and the associated perception software to understand the environment.

3.  Analog Chips for Sensing: ICs that interface with the physical world (e.g., motor drivers, power management, sensor signal conditioners).

Analysis: Seeing Machines’ relevance to areas 1-3

Seeing Machines’ core technology is AI-powered occupant and driver monitoring systems (DMS/OMS), primarily using inward-facing cameras and sophisticated computer vision algorithms. Here’s how it maps onto the humanoid robotics stack:

1. AI Brain technology: PARTIAL / INDIRECT FIT

Seeing Machines is not a semiconductor company creating the central “brain” chips (like NVIDIA, Qualcomm, or Ambarella). However, their value is in the specialized AI algorithms and software that would run on those brains.

Their ‘AI brain’ is the algorithm stack: Their proprietary expertise in gaze tracking, eyelid closure detection, head pose estimation, and facial feature analysis represents a specialized form of AI cognition that a humanoid would need for human-robot interaction (HRI). For a humanoid to work safely and effectively alongside people, understanding human attention, intent, and state is critical.

Conclusion: They provide a crucial capability that would reside in the AI brain’s software layer, but not the semiconductor hardware itself.

2. AI Vision: VERY STRONG FIT – This is Seeing Machines’ Core Competency.

This is the area of most direct and obvious relevance.

  • Sensor Focus:While they use standard camera sensors, their entire value proposition is in **maximizing the value extracted from vision sensors**. For humanoids, robust vision is non-negotiable.
  • Algorithmic Moat: Their decades of work in attention detection (critical for vehicle safety) is directly transferable to ensuring a humanoid is making “eye contact” or understands what a human is focused on. Their facial movement and state analysis is key for natural interaction.
  • Application: In a humanoid context, this technology wouldn’t just be for safety monitoring, but for enabling fluid collaboration. For example, a humanoid could tell if a human worker is looking at it for instruction, is distracted, or needs assistance.

3. Analog chips for sensing: NO DIRECT FIT

Seeing Machines is not an analog semiconductor company. They do not design motor drivers, power ICs, or low-level sensor interface chips. Their domain is the digital and algorithmic layer that comes after the analog signal has been converted and processed.

Synthesis: where does Seeing Machines fit in the ‘Humanoid’ value chain?

Morgan Stanley notes that “most of the value creation lies with distribution.” Seeing Machines is a critical “enabling technology provider that sits between the raw semiconductor hardware and the final humanoid application, specifically in the perception and human-interaction layer.

  •   They are an ‘AI Vision & Cognition’ specialist. For humanoids to move out of controlled factories and into dynamic human environments, the ability to perceive and understand human behavior is as important as perceiving objects. This is Seeing Machines’ unique niche.
  •   They benefit from the semiconductor intensity: The more camera feeds, the higher the resolution, and the more complex the real-time analysis required, the more valuable their optimized, purpose-built algorithms become. This drives demand for the capable AI semiconductors (Area 1) on which their software runs.
  • Commercial traction dictated by ecosystem readiness: As Morgan Stanley states, ecosystem readiness is key. Seeing Machines is already a Tier-1 automotive supplier with a proven track record of delivering reliable, safety-critical vision systems. This certification pedigree, system integration expertise, and understanding of functional safety (ASIL levels) are immensely valuable and transferable to the humanoid space, where safety is paramount.

Conclusion

Yes, Seeing Machines’ technology is of significant potential use, primarily and most powerfully in Area 2 (AI Vision), and as a specialized software layer contributing to Area 1 (AI Brain capabilities).

They do not make the semiconductors themselves, but they are a quintessential example of a company that creates immense value by enabling those semiconductors to perform a specific, critical, and high-value task —in this case, understanding human state and attention.

As humanoid developers shift focus from pure mobility to advanced human-robot interaction, companies like Seeing Machines, with deep expertise in human-centric vision AI, become essential partners. Their automotive-grade experience makes them a credible and valuable candidate for the ecosystem Morgan Stanley describes.

Home care robots

I then asked it: “Wouldn’t a robot humanoid used in the home, for instance to care for an elderly, possibly infirm. individuals benefit greatly from having human behaviour monitoring (provided by Seeing Machines technology) among its repetoire?”

It answered: 

Absolutely, unequivocally yes. This is not just a benefit; it is likely a non-negotiable requirement for safe, effective, and socially acceptable deployment of humanoids in a personal care context.

Extending our previous analysis, here’s a detailed breakdown of why Seeing Machines’ core competency in human behavior monitoring would be critical for a domestic care humanoid:

1. Safety as the paramount concern (The ‘Do No Harm’ imperative)

  • Fall Prevention & Detection: A humanoid could use Seeing Machines’ gaze tracking and head pose estimation to understand if the individual is looking at an obstacle, is disoriented, or is about to lose balance. Pre-emptive warning or physical assistance could be initiated.
  • Medical emergency detection: Algorithms for micro-sleep detection, eyelid closure, and loss of attentiveness—pioneered for driver drowsiness—are directly applicable to spotting signs of stroke, diabetic shock, fainting, or sudden medical distress.
  • Safe physical interaction: To assist with lifting or mobility, the robot must know where the human is looking and if they are anticipating the movement. Understanding human attention and intent prevents startling the individual or causing a mishap during physical contact.

2. Enabling effective care & assistance (beyond physical tasks)

  • Medication adherence: The robot can confirm, through gaze and facial action recognition, that a pill was actually taken and swallowed, not just lifted to the mouth and palmed. This solves a major problem in elderly care.
  • Cognitive state monitoring: For individuals with dementia or cognitive decline, changes in facial expression, engagement, and interaction patterns are key indicators. The robot could monitor for signs of confusion, agitation, or withdrawal and alert remote human caregivers or family members.
  • Companionship & engagement: The technology enables socially aware interaction. The robot can tell if its attempts at conversation or activity suggestions are being met with engagement or annoyance, and adjust its behavior accordingly. It can maintain ‘eye contact’ during conversation, a fundamental building block of trust.

3. Building trust and acceptance (The human-robot bond)

  • An elderly individual is far more likely to accept and rely on a machine that demonstrates it ‘sees’ and ‘understands’ them. A robot that blankly stares while helping someone bathe is unnerving. A robot that glances away to provide privacy, or that recognizes a facial expression of pain or embarrassment and responds with reassurance, builds essential trust.
  • This capability transforms the robot from a tool into a perceptive agent, which is psychologically critical for long-term in-home adoption.

How this fits the Morgan Stanley ‘value’ thesis

Morgan Stanley argues most value lies in distribution and enabling technologies. In the home care distribution channel, the ‘killer app’ is not mobility or strength, but empathetic, safe, and perceptive care.

  1. Ecosystem readiness: Seeing Machines is not starting from scratch. Their FOVIO chip (now in its next-gen form) and software are already ASIL-B certified for automotive safety. Translating this to a functional safety standard for robotics (e.g., ISO 13482) is a logical step. Their proven ability to ship millions of units in the harsh, safety-critical automotive environment is a massive credibility advantage.
  1. Commercial traction dictator: ‘Realistic adoption timelines’ for home care robots will be gated by safety and social acceptance regulators (e.g., FDA for ‘care’ functions, consumer protection agencies). A provider with a certified, explainable, and validated system for human state monitoring will have a tremendous regulatory and liability advantage. This directly accelerates commercial traction.
  1. Value capture: As an enabling technology, Seeing Machines could capture value through licensing their perception software stack or providing a complete ‘Human understanding module’ (sensor + dedicated processor + algorithms) to humanoid makers. The value of their IP in ensuring the robot doesn’t cause a catastrophic failure in a vulnerable person’s home is immense.

In summary: For a domestic care humanoid, human behavior monitoring is not a ‘nice-to-have’ feature in its repertoire; it is the foundational layer for its core value proposition

Seeing Machines’ technology provides the ‘eyes’ and, more importantly, the ’social brain’ that would allow such a robot to navigate the profoundly complex, unstructured, and emotionally charged environment of a human home.

It directly addresses the primary barriers to adoption: safety, efficacy, and trust. Therefore, Seeing Machines’ technology sits squarely in the highest-value layer of the ecosystem Morgan Stanley describes.

My view

I believe Mitsubishi has already identified this value. That is why it took a 19.9% stake in Seeing Machines. It currently seeks to use its technology in automotive robots (cars), then plans to use it in industrial robots, before expanding into home care robots.

Does that sound a little far-fetched to some? 

Well, Paul McGlone has admitted that Seeing Machines is discussing expanding the use of its technology into ‘smart factory’ use with Mitsubishi. Industrial robots are absolutely central to Mitsubishi’s smart factory vision.

Mitsubishi’s first humanoid robot, launched 20 years ago, called Wakamaru wasn’t a success. Yet, if it developed a ‘Human understanding module’ with Seeing Machines technology, I believe there is the potential to build a home care robot that could be.

Of course, there are many other companies making huge bets on humanoid robots, notably Tesla. They might also be keen to acquire the technology and IP that Seeing Machines possesses. 

I’d urge investors to research this area and decide for themselves whether there is merit in my arguments. 

The writer holds stock in Seeing Machines.

Seeing Machines wins contracts worth $11.6m 

Seeing Machines (AIM: SEE) has announced an additional $10m auto win with a European customer and a new win with a Japanese car manufacturer worth $1.6m, taking its pipeline of contracts wins to over $400m.

European win

The European win is with an OEM that already has a production in development with SEE, and this extends its agreement for production volumes beginning in 2028 through to 2031. 

According to analyst Peter McNally at house broker Stifel, this could be the first of many extensions as the life-saving technology becomes mandatory for all vehicles in Europe. McNally stated: “We think this could become a typical announcement for the company, as we believe it has a large part of the European market based on the statistic released at the FY26 results, i.e., that its OEM customers are forecast to sell circa 12.5m of the estimated circa16.0m cars in Europe in 2026.”

Japanese win

In addition, Seeing Machines has been appointed by Mitsubishi Electric Mobility Corporation (MELMB) to deliver a small program for a leading Japanese OEM, with production scheduled for 2028. In the RNS issued today, SEE stated: “This program, with an initial value of US$1.6m, reinforces Seeing Machines’ long-term growth strategy with MELMB in Japan, and the company is confident of securing additional opportunities as this progresses.”

It added: “These new business awards bring the total cumulative initial lifetime value for all Seeing Machines Automotive programs won to date, to over US$400m, the majority of which is expected to be received by 2028.”

AGM news

Separately, at the company’s AGM earlier today, CEO Paul McGlone revealed that the Mitsubishi trial of Guardian Gen 3 in trucks has been successful.

Importantly, McGlone also confirmed that Seeing Machines is on track to hit its breakeven “runrate” as of the end of December so, in effect, Q3 of this financial year should be its first cashflow positive quarter.

McNally in his note wrote that the biggest hurdle remains the Magna loan but reassured investors that “
given the DMS ramp and our expectation of positive cash flows in the back half of 2026, we think it will have financing options available to it from a variety of sources”.

Personally, I expect Magna will be more than happy to take shares in lieu of repayment as Seeing Machines price rises above 10p over the next couple of months – driven by further contract news and the confirmation that it has hit breakeven, with profitability assured. Thus, the Magna loan is effectively an issue that should not overly concern shareholders.

The writer holds stock in Seeing Machines.

Seeing Machines seals Amazon contract in the US

Seeing Machines (AIM: SEE) has finally won the Amazon.com contract for Guardian Gen 3, which should be the first of many decent-size Gen 3 contracts over the next few months. 

In an RNS issued today Seeing Machines confirmed that it has won the “US-based multinational” and would support the initial installation of 1,100 Guardian units, which are scheduled for completion by this December. Discussions are also ongoing for further expansion in the New Year for Amazon’s heavy truck fleet.

According to information I’ve obtained (which are likely to be an underestimate), Amazon in the US has a fleet of approximately 1,645 tractors (cabs) and 12,835 trucks. 

KPIs

Seeing Machines also released its latest set of KPIs for Q1 FY 2026, with confirmation that it now has 4.24m cars on the road with its DMS technology. An additional 510,000 cars were produced in the latest quarter, 4% up on the previous quarter, demonstrating continued growth in what is traditionally a subdued quarter.

Sales of Guardian Gen 3, at 368, did disappoint. However this was due to delayed large deals, which are now coming through as is clear from the Amazon win.

In a note issued today, analyst Peter McNally from house broker Stifel commented: “Guardian unit sales in the quarter were 368 (fiscal Q425: 2,536) as certain expected deals slipped into the current quarter, including a significant aftermarket order announced today for the 1.1k units before December 2025. This means that shipments in Q2 so far are already greater than 2,600 units and therefore have been more of an issue of timing rather than quantity, as we are less than halfway through fiscal Q2.”

He added: “The aftermarket pipeline remains healthy, with multiple pilots and commercial contracts progressing, and partnerships such as Mitsubishi Electric Automotive America expected to support production scaling through FY26. We estimate current quarterly capacity at roughly 6k units with c.$800 ASP and ~40% gross margin, highlighting improved unit economics versus Gen-2 and stronger leverage potential as volumes rebuild.”

Importantly, CEO Paul McGlone has confirmed: “We remain on track to achieve our cashflow break-even run rate target by the end of this calendar year.” 

While some traders have cashed out their winnings, most investors are holding as the share price rise seems set to continue, as auto volumes ramp in anticipation of EU legislation that comes into force in July 2026. Also, tougher Euro NCAP safety ratings apply from January 2026 and will necessitate a camera-based DMS/OMS for a car to achieve a 5 star safety rating.

McNally’s view is clear: “We expect momentum to build through FY26 as full compliance with the July 2026 GSR mandate approaches. Seeing Machines remains the DMS market leader with over 4.2m vehicles deployed, ahead of Smart Eye (~2m). With customers representing c.12.5m of the 16.1m European vehicles forecast to be sold in Europe in 2026, the installed base should continue compounding, though the pace of inflection will vary by OEM depending on inventory and model cycles.”

In addition, I expect multiple new contract wins in auto and aftermarket to materialise by Christmas.

The writer holds stock in Seeing Machines.

Seeing Machines is a strong buy

Today’s RNS announcing yet another contract for Seeing Machines Gen 3 Guardian aftermarket product is further confirmation that the company is set to hit cashflow breakeven by the end of this calendar year. 

Although the bus manufacturer wasn’t named directly, the 5-year contract must surely be with Wrightbus with whom Seeing Machines was already supplying its Guardian Gen 3 driver montitoring technology, after achieving homologation in July 2024.

Homologation for Gen 3 Guardian is also taking place with another 4 OEMs, representing 4,000 additional vehicles annually.

This follows a very positive video presentation yesterday from CEO Paul McGlone and CFO Martin Ive, in which they confirmed:

  • Seeing Machines is on track for cashflow breakeven by the end of this calendar year.
  • Approximately 2m cars a quarter will be hitting the road with its DMS from July 2026 (around 33 minutes 40 seconds). 
  • OEMs are collectively telling Seeing Machines that half of the auto RFQs that SEE has worked on are planned to be awarded by December this year, with the other half due in the second half of this financial year. (From around 15 minutes and 10 seconds)
  • Following successful trials, they are in final stage, “commercial negotiations” for the biggest ever Gen 3 contract in the US and another big one in the EU.  (Around 19 minutes).

I personally think the US negotiation is with Amazon and the European one is with Shell, which was surely the company mentioned in today’s RNS: “The company is also progressing towards a European-wide contract in the Oil and Gas sector, with Guardian already deployed in the UK and four other European countries.”

Peter McNally, analyst at house broker Stifel, in a typically perceptive flash note added that the current number of units deployed by this oil & gas major is 200. Therefore, I’m expecting many multiples of this when Shell finally sign the latest Gen 3 contract. Shell places great emphasis on improving safety outcomes and Guardian Gen 3 will deliver that.

I’m shocked that Seeing Machines is still sub 3p but, when the sceptics realise that it’s no longer a jam tomorrow company, rather a jam factory, that price will shoot up. 

Refinancing not an issue

Even the issue of refinancing the Magna loan of approximately $62m should hold no terrors, as Peter McNally pointed out in a note yesterday:

“Seeing Machines’ convertible loan comes due in October 2026 and unless shares go through the conversion price of 9.95p, it will likely have to refinance $61.9m of debt. We think there’s a small chance that Magna could extend the loan, but we don’t rely on that happening. Rather, we think the company will be in a good position to refinance.”

Personally, I expect the issue will disappear as the share price quickly goes north of 10p. Moreover, I do still expect Mitsubishi to make an offer for Seeing Machines before then. 

Mitsubishi partnership

This isn’t mere conjecture. In yesterday’s video presentation Paul McGlone even laid it out before investors; that Mitsubishi is leading discussions as to how Seeing Machines technology can be used in adjacent markets (9m) to benefit Mitsubishi.

“With Mitsubishi working with us in parallel they’ve identified a range of new adjacent markets where they have significant strength around the world, and we are now in the early stages of planning to determine where we can implement our technology to ENHANCE THEIR EXISTING CAPABILITIES (my emphasis). And of this portfolio of  opportunities 
both insurance and smart factory are the ones that we’ve prioritised together and are being led by Mitsubishi.”

To me it’s crystal clear that Mitsubishi needs and wants Seeing Machines. Still, it’s not the only company that is likely to bid for Seeing Machines, as previously stated. Admittedly, the timeline for a bid is probably more likely to be April 2026 than this year – but that’s not so long to wait. Moreover, it makes a higher price more likely. What’s not to like?

How many times does an investor get to buy a stock that is set to go up at least 5-10x in a year? Of course, do your own research – but don’t be too long about it.

The writer holds stock in Seeing Machines.

Mitsubishi to buy Seeing Machines by Christmas?

Despite Seeing Machines share price being in the doldrums, I’m optimistic that breakeven (on a monthly basis) later this year will be swiftly followed by a takeover offer from Mitsubishi. If my calculations are correct this could happen as soon as this Christmas.

Although I don’t have definitive proof, I hope even my harshest critic could not fairly accuse me of laying out before you a ‘delusional’ scenario. Indeed, there is an ineluctable logic to Mitsubishi moving to buy Seeing Machines in a friendly takeover by early December.

Why Mitsubishi? 

There are a number of reasons why I believe Mitsubishi is most likely to acquire SEE. Mitsubishi holds 19.9% in Seeing Machines, their engineers are working together developing advanced driver monitoring features, Mitsubishi is helping increase sales of Guardian Gen 3, and Mitsubishi has the resources eventually to use the technology in everything from fork lifts to robots. Indeed, more immediately, the wide range of activities of this Japanese group shows an almost perfect fit with SEE’s 3 divisions; Auto, Aftermarket and even Aviation.

There is also a strong cultural fit, as this Japanese company prefers a consensual approach to a takeover. This fits with the Australian preference for a scheme of arrangement for a friendly takeover of an Australian listed company.

Why this year? 

Firstly,  despite being delayed, breakeven on a monthly basis is forecast to occur before December. Fortunately,  Euro NCAP and GSR2 regulation compel the road transport industry to accelerate the introduction of camera-based driver monitoring, and we’ll see increased license royalties from auto and sales of Guardian Gen 3. 

Seeing Machines should also have significant additional contract wins in Auto and Aftermarket over the coming months, confirming its dominant position as the number one global player in advanced, camera-based driver/occupant monitoring (morphing into interior monitoring) for years to come.

Breakeven with a pipeline of contracts guaranteeing significant profits should trigger buying from fund managers who’ve been patiently sitting on the sidelines. More importantly, it would likely reinforce Mitsubishi’s determination to follow through with its plan. I say ‘plan’ because this is clearly a strategic move that has been on the cards for a while.

Mitsubishi has already conducted extensive due diligence prior to investing in Seeing Machines and, with its near 20% stake, has a slight advantage over other potential buyers. It also makes sense for Mitsubishi to buy Seeing Machines just before it becomes highly profitable, otherwise the acquisition price could quickly spiral upwards.

Interestingly, the personal interests of CEO Paul McGlone and that of investors in Seeing Machines appear closely aligned: a bid would be at a premium to the share price (certainly multiples of its current price of approximately 2.5p) and enable him to secure his 25m performance shares before his current contract expires on June 30, 2026. It’s all detailed in the last annual report on Page 67, for those unfamiliar with the details. Note the target share price (TSP) needed for the CEO to secure the maximum number of his 25m performance shares is 20p.

Given the time it takes to process a scheme of arrangement (normally 3 months) and the fact the Australian Court is closed from mid-December to February, for Seeing Machines to be confident of closing the deal before Paul McGlone’s contract expires, early December 2025 seems the latest date that any potential deal would be announced.

The CFO Martin Ive has also been steadily hoovering up shares. Surely he is confident of a significant price rise when SEE achieves the long-awaited breakeven? Warren Buffett would certainly approve, having advised: ‘Be fearful when others are greedy and greedy when others are fearful”.

Price

What sort of price do I expect Seeing Machines investors to receive if this scenario pans out? I think the best they could hope for would be somewhere above 20p but probably below 40p. It’s unrealistic to expect more unless other bidders suddenly materialise. Still, by agreeing to a price well above 20p Mitsubishi could reduce the odds of that happening. 

I doubt the management of Seeing Machines, never mind the funds holding it, will look kindly upon a price below 20p given the huge rise in auto royalties that are guaranteed, not to mention the contract wins expected across all 3 divisions. Moreover, they’re probably in a position to encourage other bidders to step in were Mitsubishi to try. However, I think Mitsubishi has more honour and sense than to even attempt a low-ball offer.

Battle of the Titans

Regardless of the eventual price agreed by Mitsubishi and Seeing Machines, I wouldn’t completely rule out the possibility of other companies stepping in with hostile bids, which would start the long-awaited ‘Battle of the Titans’. The list of potential rival bidders is long and could include one or more of the following: 

  • Amazon
  • Alphabet
  • Apple
  • Raytheon (parent of Collins Aerospace)
  • Qualcomm
  • AMD
  • Nvidia
  • Mobileye
  • Magna 
  • Valeo
  • Tesla

There might also be left-field entrants or a bid from a private equity player. Alas, the state of the world being what it is, I don’t think  a bid from a Chinese company would stand a chance of being accepted.

Crucially, it would take a big number to hijack what, to me at least, seems to be a very likely deal. Yet, in the above list of rival potential bidders there are some huge hitters.

Of course, I’m not Nostradamus and my assumptions could be completely wrong. Therefore, it’s advisable to do your own research and always invest only what you are prepared to have tied up for a while, never mind lose.

The writer holds stock in Seeing Machines.

Stellantis confirms DMS across all models for Europe by mid 2026

Speaking exclusively to this journalist, Stellantis has confirmed that it will be putting driver monitoring into all its European cars by mid-2026. Furthermore, I believe Valeo and Seeing Machines are the suppliers of its latest interior monitoring technology, which is set to go into production this summer.

A spokesperson for Stellantis confirmed to me this week that: “As DMS becomes a regulatory requirement, all new Stellantis vehicles registered in the UK and EU will feature the system by mid-2026. Some models will adopt it earlier if they are classified as “new types” under the EU General Safety Regulation.”

The reason I’m so confident that Seeing Machines is the supplier of the DMS/OMS system in partnership with Valeo as the Tier 1 is because the announcement ties in with other evidence.

Evidence

Firstly, Safestocks previously confirmed that two previous wins for Seeing Machines, in June 2022 and December 2022 were with Stellantis. 

Secondly, we know that Seeing Machines and Valeo are partnered for interior monitoring and Colin Barnden, in a LinkedIn post dated April 7th 2025, confirmed Seeing Machines and Valeo as working with Stellantis. Barnden commented: “QNX Cabin was demonstrated at CES 2025 running on a Qualcomm SoC, possibly the 4th generation cockpit processor, with DMS from Seeing Machines. So we can start to piece together a partnership encompassing Qualcomm/QNX/Seeing Machines, the first example of which appears to have reached production with Stellantis running DMS in the cockpit SoC.

“Qualcomm has previously stated the DMS can run in an accelerator on either the Snapdragon Ride or Snapdragon Cockpit processor, and the decision is left up to the automaker. So, at long last, we appear to have some evidence of the link between Qualcomm and Seeing Machines showing up in a vehicle at start of production. This information may also reinforce the conclusion that the tier-1 for the Stellantis program is Valeo, rather than Magna International.”

Lastly, at the recent Town Hall event, Martin Ive, Seeing Machines’ CFO, stated: “We also have 2 new OEMs going into production over the summer with a different Tier 1 [Ed – as VW is already in production with Magna, it must be Valeo]. They will add significant volume as we go through the calendar year, probably hitting more so with the ramp up in production by the time we come to the December quarter.”

Nothing in life is certain and, in the world of automotive, NDAs make it necessary to put together various pieces of evidence to draw conclusions. However, I’m sufficiently confident that Seeing Machines is the supplier to Stellantis to state it publicly. I hope it is of interest to investors as, to me, it confirms that Seeing Machines is set to dominate interior monitoring in passenger cars at least until 2027. 

Of course, I expect it to do so long after that date but probably under different ownership — I will explain all about that in a subsequent blog post.

Doubters should remember that Martin Ive himself stated at the recent Town Hall event that he expects (after discussion with OEMs and Tier 1s) that Seeing Machines auto volumes in Europe will go up 10x from 160k to 1.6m a quarter by June 2026, 2m overall. 

Of course, investors should do their own research and beware traders seeking to influence their views.

The writer holds stock in Seeing Machines.

Why Seeing Machines should be included in the ‘Humanoid 100’.

As Morgan Stanley recently outlined in a broker note, robots represent the physical embodiment of AI, which appears to be why they are in the process of becoming THE hottest sector of tech. Yet, despite producing a brilliant note Morgan Stanley has overlooked one key player in its round-up of the top 100 players; Seeing Machines.

That may well be because, unlike the likes of Mobileye, Alphabet and Meta it has a miniscule market cap and resides in a stockmarket slum called AIM. Regardless, someone soon is going to want to marry this beauty. Let me explain why.

To quote the broker note of 6th February: “The physical embodiment of AI touches a $60tn Total Addressable Market (TAM), global GDP, and the meaning of work.”

In that note Morgan Stanley presented the ‘Humanoid 100’, which it described as “a global mapping of equities across a range of sectors and regions that may have an important role in bringing robots from the lab to your living room”.

It used this graphic to illustrate a rudimentary division of these companies into those developing the brain and body value chains.

I’d argue that Seeing Machines should be included in the portion of the Brain (Vision & Compute Semiconductors), which as it currently stands is overly simplistic. For true robots to be successful they will need to develop an understanding of the cognitive state of humans, perhaps even display traits we’d associate with empathy. 

I think SEE sits in the same niche as Mobileye in that diagram. “These are the companies producing semiconductors that are the core of the robot “brain”, allowing robots to learn from, perceive, and/or interact with their environments. Vision-focused semis lie at the edge and allow robots to visualize their environments,” states the note. However, Seeing Machines does something special: it allows robots to visualise humans


It is Seeing Machines, with its software and hardware, that can literally breathe life into robots. As Victor Frankenstein would have exclaimed: “It will pioneer a new way, explore unknown powers, and unfold to the world the deepest mysteries of creation.”

Mobile robots

Still skeptical? Well, Seeing Machines is displaying that technological capability and is applying it to mobile robots; cars, with its AI-powered driver monitoring.

Its technology uses advanced machine vision technology to precisely measure and analyse head pose, eyelid movements and eye gaze under a full spectrum of demanding in-vehicle lighting conditions. This data is then processed to interpret driver attention state, drowsiness, and impairment levels.

That same technology is also enabling an eco-system that provides highly intelligent vehicle interfaces that employ AI to not just respond to speech commands, but to understand more subtle cues from occupants as indicated by hand gestures and eye movements.

Is it so fanciful to imagine that in the near future the ability to assess reduced cognitive ability and understand more subtle clues could be vital for ‘care’ robots used to look after elderly or vulnerable charges. 

Recognition of its ability in the transport sector has brought partners rushing to sign deals with Seeing Machines – many of whom feature in the ‘Humanoid 100’ list. Yet, its latent qualities in the sphere of robotics remains unrecognised by most. Hence, its current market cap belies the true value within. That cannot last much longer
 Do you hear wedding bells?

The writer holds stock in Seeing Machines.

Volkswagen’s small ‘BEV for All’ will feature Seeing Machines technology

Volkswagen has confirmed that its Volkswagen ID2, set to go on sale in 2026, will feature a camera-based driver monitoring system (DMS) in its rear view mirror. Powered by Seeing Machines technology it is expected to feature both driver and occupant monitoring.

This small battery electric vehicles (BEV), based on the ID2.all concept, which was revealed in 2023, is intended to be a huge seller for the German car company. It is expected to retail for around ÂŁ22k for the entry-level model. 

As a spokesperson for Volkswagen confirmed: “The all-new Volkswagen T-Roc and our up-coming small BEV will be the next vehicles to be equipped with the camera-based DMS from start of production. Since the function (Attention and Drowsiness Assist) will be required by EU law from mid-2026, we are working on equipping all other vehicles with a camera-based DMS.”

Seeing Machines has previously stated that when it comes to cost and packaging complexity, its integrated rear-view mirror (RVM) solution, offered exclusively by the Tier 1 Magna, is best in class.

I’m therefore expecting many other car manufacturers who are late to the DMS/OMS party (but whose cars sell in Europe and are therefore required to meet GSR2 mandatory safety legislation) to choose the rear view mirror solution for their new cars.

Seeing Machines’ cutting-edge DMS/OMS is also available in a two camera-solution, should car manufacturers wish to use that.

The writer holds stock in Seeing Machines.

Disappointing growth, SEE’s broker downgrades

Following Seeing Machines’ disappointing first half Trading Update combined with quarterly KPIs, both house broker Stifel and Peel Hunt downgraded their price targets and cut revenue expectations, while increasing their estimates for the losses expected for this year. 

In terms of the KPIs: cars produced with SEE technology grew more slowly than expected, falling 34% to 267K in 2Q25 compared with the previous quarter. In addition, sales of Gen 3 Guardian were only 288, making just 1,779 units sold in the first half of the 2025 financial year.

House broker Stifel’s Analyst Peter McNally cut his Price Target from 11.4p to 9.6p but maintained his ‘Buy’ recommendation. McNally summarised his view as follows:

“Seeing Machines’ H1 performance is indicative of wider auto industry struggles, with broadly flat revenues and ARR, leading to a larger-than-expected adjusted cash EBITDA loss of $17.5-18.0m. 

However, cost initiatives over the past 12 months and further planned in H2’25 should reduce cash operating expenses significantly. We also highlight the recent $32.8m strategic investment from Mitsubishi Electric Mobility, which provides  stability as the company gets closer to reaching cash flow breakeven.

While cars on the road has been healthy with 90% y/y growth, Q2 production was down 34% q/q. Although there is a lack of certainty with regard to when exactly this volatility will reverse, we still expect a strong tailwind from the approaching GSR deadline (July 2026) as it moves closer.

Sales of Aftermarket Guardian 3 units have also faced slight delays, however we expect sales to accelerate in H2 as a result of a full commercial release and benefit from the new referral agreement with Mitsubishi Electric Automotive America, which opens the Guardian 3 up to a 1m+ vehicle fleet market.

We reset revenue estimates to a more conservative level based on market uncertainty, but do expect a reduction in the cost base by FY26E to mitigate much of this in FY26/27E. We moderate our target price to 9.6p (from 11.4p) to reflect these new forecasts.”

Explaining in more detail his changes in forecast and valuation, McNally said: 

“We reduce FY25-27E revenues by $10m, primarily as a result of softer royalties, prudently assuming that production volumes do not pick up in FY25E, with possible upside. While the FY25E adj. EBITDA loss increases by $7.5m to $24.4m, we expect the revenue reduction beyond FY25E to be largely mitigated by cost initiatives and as a result we reduce adj. EBITDA profit by just $2m in FY26/27E. As a result of our forecast changes, our DCF-based target price reduces to 9.6p (11.4p). At current levels the shares trade at 3.6x our FY25E EV/Sales, or 11.8x FY26E EV/EBITDA. Buy.”

In addition, Peel Hunt today downgraded from a ‘Buy’ to ‘Reduce’, slashing its Price Target from 7p to 3p. In its note, analysts wrote: “We cut FY25/26/27E revenue by 17%/19%/10% to reflect weaker automotive demand and the slow start from the Guardian generation 3.”

My view

Naturally, I’m disappointed by the update today. I had expected cars on the road to whizz past 3m, despite volatility in the auto market. I didn’t expect car makers to sacrifice safety in an effort to cut costs, thereby risking reputational damage by producing more dangerous cars for consumers. It is shocking that saving lives from driver fatigue and distraction is deemed a lower priority than making profits. Still, it highlights why regulation (in the form of GSR) and pressure from Euro NCAP are vitally important in forcing car manufacturers to improve car safety.

I don’t hold the management of Seeing Machines responsible for this atrocious attitude from car manufacturers, although it has clearly impacted revenues in the short term – and is likely to continue for two more quarters we’ve been advised.

Still, it shouldn’t be ignored that Seeing Machines continues to have more cars on the road with its technology than any of its rivals and I don’t expect this to change.

That is because I expect Seeing Machines to win a significant share of the RFQs that are currently underway. News of a significant contract win could ease investor concerns and encourage brokers eventually to upgrade estimates.

However, I’m far less forgiving of the time it has taken to ramp up production of Guardian Gen 3, which to be frank was late to launch and has so far sold only in small volumes. It’s no wonder many private investors have sold out. However, given CEO Paul McGlone’s statement in a video interview with Tylah Tully that there are 7 significant trials in progress – one of which I believe is Amazon – I hope that things are now on track for significant sales in the final quarter of this financial year. 

Fortunately, the company currently has a $39.6m cash balance and time to set things right before the end of this financial year.

Personally, I’m prepared to hold as I expect the share price to rebound on contract news before the end of this financial year. However, do your own research.

The writer holds stock in Seeing Machines.

Mitsubishi’s strategic stake in Seeing Machines

A few thoughts on the strategic investment in Seeing Machines taken by Mitsubishi Electric Mobility Corporation, part of the huge Mitsubishi conglomerate.

  • It secures the cash for Seeing Machines to hit breakeven regardless of the vagaries of the economy, automotive sector or machinations of any single industry player or partner. 
  • It ensures that when a bid is made for Seeing Machine it will be at a very competitive price. The company cannot possibly go on the cheap. 
  • It provides a local partner in the Japanese market, which should make it much easier to gain a strategic stranglehold in the Japanese automotive sector, while also ensuring further diversification in its Tier 1 relationships.
  • Via Mitusubishi’s network we should see Gen 3 Guardian sales in trucks rocket from here on in. It also produces and sells buses and trucks via the FUSO brand – a collaboration with Daimler Trucks. 
  • It potentially opens up new markets to Seeing Machines technology. Mitsubishi manufacturers road construction, agricultural equipment and even forklifts, which could use Seeing Machines’ driver monitoring technology to reduce accidents caused by driver fatigue.
  • The fact that Mitsubishi was determined to take the maximum percentage of shares it could take without triggering a bid (19.9 per cent) tells me how highly it values this investment. It plans to develop more personalised robots in the future for a rapidly ageing society in Japan and combining Seeing Machines’s human fatigue/cognitive state detection with heartbeat detection would be useful features for a domestic ‘carer’ robot to have. 

Consumer Electronics Show

With the Consumer Electronics Show (Jan 7-9) expected to bring news of further license deals, the list of possible buyers of Seeing Machines grows ever longer. 

Moreover, in calendar 2025 I expect its market leadership to become both undeniable and unassailable in the medium term, as:

  • It surpasses 5m cars on the road with its DMS/OMS technology
  • It becomes profitable on a monthly basis by June.
  • Guardian goes past 100k units.
  • The Aviation product is readied for use. 

VW Tayron on sale now

The Volkswagen Tayron, which includes Seeing Machines DMS in its rear view mirror, is due to go on sale in the UK this week. 

The first UK reviews of the vehicle should take place in the spring, possibly mid-to-late March; there may well be some reviews from overseas drives before that, in late February or early March.

This should rapidly boost the profile of its life-saving technology, not to mention public interest in buying shares in a tangible AI product.

The writer holds stock in Seeing Machines