VERSES® Unveils Robotics Architecture that Works Without Pre-Training
VERSES multi-agent robotics model show to outperform current methods on Meta’s Habitat Benchmark without pre-training
VANCOUVER, British Columbia, Aug. 14, 2025 (GLOBE NEWSWIRE) — VERSES AI Inc. (CBOE: VERS) (OTCQB: VRSSF) (“VERSES” or the “Company”), a cognitive computing company specializing in next-generation agentic software systems, today unveiled details on the development of its robotics model.
The VERSES robotics architecture accomplished typical household tasks of tidying the room, preparing the groceries, and setting the table, better than other robotics models and VERSES accomplished the tasks without any pre-training. A video of the robot performing these tasks can be seen on the VERSES website https://www.verses.ai/blog.
Robots often perform well on scripted tasks but can freeze when faced with new situations; even something as simple as a box in the wrong place can halt progress. Newer approaches can be more flexible but require huge amounts of training to be effective. This makes existing robotics solutions difficult to use in real-world applications where new situations constantly arise. Challenges like this are well suited to VERSES models’ abilities for quickly adapting to their environment.
“Currently robotics systems are often brittle, and need huge amounts of training data, which makes them expensive and prone to going wrong.” said Sean Wallingford former CEO and President of Swisslog, one of the world’s leading logistics automation companies. “For instance, if you bring a robot to a new factory or ask it to do a different job, it will need a lot of re-training and may not be reliable. VERSES breakthroughs are exciting, because they offer an alternative approach. If we can deploy robots without training, they will be viable in a wide range of activities, from factories and warehouses to domestic and commercial applications.”
In a published paper entitled, “Mobile Manipulation with Active Inference for Long-Horizon Rearrangement Tasks” written by members of the Company’s research lab, the VERSES robotics model is compared to a deep learning alternative in three tasks: tidying a room, preparing groceries, and setting a table. The VERSES robotics model achieved a success rate of 66.5% across these tasks while the previous best alternative had a success rate of 54.7%. The VERSES robotics model also requires no training, whereas the other robotics model required 1.3 Billion steps to pre-train several skills across the three tasks.
“I believe that by combining our world-modeling and our active inference capabilities, we’ve shown robots can think on their ‘feet’ — navigating and completing complex tasks without months of costly training.” Hari Thiruvengada, VERSES CTO, said, “Our breakthrough has the potential to transform how robots operate across industries, from factories and warehouses to homes and public spaces, potentially unlocking a new era of truly adaptive, reliable automation.”
Notes to editors
- The leading model in the Habitat rearrangement challenge was “Multi-skill mobile manipulation”. Further details can be found here: https://aihabitat.org/challenge/2022_rearrange/
- Further details can be found below:
Robots generally fall into two categories: drive-by-wire or deep learning. Drive by wire means everything is pre-programmed. Deep learning relies on vast amounts of data for training.
Autonomous Guided Vehicles (AGVs)
The drive by wire approach breaks down if anything is out of place.
For instance, a human might program a robot to move an object to a location by providing a very detailed list of tasks in the form of a plan (e.g. “pick an item from the shelf and place it on the shelf”) down to the specific movements needed by each joint on a robot’s arm.
However, factories and homes are always changing. Robots often struggle to adapt, which can cause them to stop or work very slowly.
To overcome their inherent limitations, robotics environments are often controlled. For instance, robots may be placed in a cage or in factory areas where no humans are allowed. This practice greatly reduces the robots’ usefulness.
Deep learning approaches
Deep learning approaches by contrast, are trained on vast volumes of data, so that they are more flexible.
However, these methods struggle with situations outside their training. Simple issues, like a bottle falling over or a chair being out of place, can confuse and paralyze the robot as it cannot adapt.
For instance a robot replenishing a production line in a factory may not be adaptable enough to switch aisles, when its initial route is blocked. Or if it is placing a bowl on a table, it may not be able to adapt to existing objects such as a wine glass, even if it has placed them there itself.
VERSES solution
We have solved this problem of adaptability.
When a human needs to get a drink in a new apartment, they don’t execute by having practiced this task in hundreds of different apartments, they are able to adapt because they have a model of how the world works. This allows humans to figure out that they need to open the refrigerator and grab a bottle. VERSES technology equips robots with a world model, allowing it to execute three tasks in different apartment layouts.
VERSES models, similar to our work on the AXIOM digital brain, don’t require any pre-training and instead just adapt by exploring the environment.
VERSES models consist of three modules working together:
- Vision: Taking pixels and turning them into understanding as well as mapping the room it is in.
- Planning: It can take a task such as setting the table for dinner and plan out all the subtasks (e.g. opening a drawer, and putting cutlery on the table) without needing detailed instructions –
- Control: Translating these into all the specific movements of the robot and its arm.
At each stage, the VERSES system can adapt – for instance it can cope with unexpected objects in its way, or needing to pick up something it has dropped.
In a paper which we will present at the International Workshop on Active Inference later this year, we will demonstrate how the VERSES models compare to a leading model, across three tasks ‘TidyHouse’, ‘PrepareGroceries’, and ‘SetTable’.
Comparing the three tasks combined, VERSES achieved a 66.5% success rate compared to the 54.7% of the leading baseline (known as ‘Multi-skill mobile manipulation’).
Critically, the VERSES model needs no training. All the VERSES model news is basic knowledge such as its own arm resting pose when idle or how much resistance the arm will gets from obstacles. By contrast the baseline model requires extensive offline training of 6400 episodes per task and 100 million steps per skill across a total of 7 skills, such as picking up an object or opening a fridge.
Use cases for this work include moving inventory around factories and warehouses.
The paper can be found at https://arxiv.org/abs/2507.17338 and additional details are available at https://www.verses.ai/blog
About VERSES
VERSES® is a cognitive computing company building next-generation agentic software systems modeled after the wisdom and genius of Nature. Designed around first principles found in science, physics and biology, our flagship product, Genius,™ is an agentic enterprise intelligence platform designed to generate reliable domain-specific predictions and decisions under uncertainty. Imagine a Smarter World that elevates human potential through technology inspired by Nature. Learn more at verses.ai, LinkedIn and X.
On behalf of the Company
Gabriel René, Founder & CEO, VERSES AI Inc.
Press Inquiries: press@verses.ai
Investor Relations Inquiries
James Christodoulou, Chief Financial Officer
ir@verses.ai, +1(212)970-8889
Cautionary Note Regarding Forward-Looking Statements
This news release contains statements which constitute “forward-looking information” or “forward-looking statements” within the meaning of applicable securities laws, including statements regarding the plans, intentions, beliefs and current expectations of the Company with respect to future business activities and plans of the Company. Forward-looking information and forward-looking statements are often identified by the words “may”, “would”, “could”, “should”, “will”, “intend”, “plan”, “anticipate”, “believe”, “estimate”, “expect” or similar expressions. More particularly and without limitation, this news release contains forward–looking statements and information including, but not limited to that the Company’s robotics models have the potential to transform how robots operate across industries, and that the Company’s robotics models could unlock a new era of truly adaptive, reliable automation.
The forward–looking statements and information are based on certain key expectations and assumptions made by the management of the Company. As a result, there can be no assurance that such plans will be completed as proposed or at all. Such forward-looking statements are based on a number of assumptions of management. Although management of the Company believes that the expectations and assumptions on which such forward-looking statements and information are based are reasonable, undue reliance should not be placed on the forward–looking statements and information since no assurance can be given that they will prove to be correct.
Forward-looking statements and information are provided for the purpose of providing information about the current expectations and plans of management of the Company relating to the future. Readers are cautioned that reliance on such statements and information may not be appropriate for other purposes, such as making investment decisions. Since forward–looking statements and information address future events and conditions, by their very nature they involve inherent risks and uncertainties. Actual results could differ materially from those currently anticipated due to a number of factors and risks. Accordingly, readers should not place undue reliance on the forward–looking statements and information contained in this news release.
The forward–looking statements and information contained in this news release are made as of the date hereof and no undertaking is given to update publicly or revise any forward–looking statements or information, whether as a result of new information, future events or otherwise, unless so required by applicable securities laws. The forward-looking statements or information contained in this news release are expressly qualified by this cautionary statement.
