Neura Robotics unveils Neuron AI robot foundation model, fusing vision, touch and audio
Germany's Neura Robotics has released Neuron AI, a robot foundation model that adds tactile and force data, audio, robot state and language on top of 3D vision, and features memory that can retain information after an object leaves the field of view. Neura plans to demonstrate it later this week at Nvidia GTC Berlin, with the humanoid robot 4NE1 completing an eleven-minute garment-handling process. The company has not disclosed the extent to which the additional sensory inputs affect performance, nor the amount of data required for training; an Interact Analysis analyst questioned whether its robot training facility can collect enough multimodal data.
Why read this
AI score 56
The report presents Neura's approach of supplementing vision with touch and sound, and also cites analysts' doubts about whether multimodal training data is sufficient.
Topics
Body
NewsRobot company bets touch, sound can give bots an edge over vision AI
Neura’s latest foundation model combines vision, touch and audio to improve robotic perception, but training it on enough real-world data could prove difficult.Scarlett Evans,Contributing Writer
October 19, 20262 Min ReadNeura Robotics
Germany’s Neura Robotics has unveiled a foundation model to help robots make decisions using touch, sound and other sensory inputs alongside vision, in a bid to improve the machines’ perception capabilities.
The new model, Neuron AI, combines 3D vision, tactile and force data, audio, robot state and language in a perception-language-action model. Neura said the design also incorporates “memory,” enabling robots to retain information about objects and previous actions even when those objects are no longer visible.
Neura is planning a live demonstration of Neuron AI at Nvidia’s GTC conference in Berlin later this week. At the demo, Neura’s humanoid robot 4NE1 will perform an eleven-minute laundry-handling sequence, trained using the new model.
The approach differs from traditional physical AI systems that primarily rely on vision-language-action (VLA) models, which use visual information to learn to perform tasks.
Related:How Boston is becoming a physical AI hub
According to Neura, Neuron AI uses three sources of data to train robots: real-world robot interactions, simulated tasks and environments, and human demonstrations captured with sensor-equipped suits.
The company collects the sensory and movement data at its Neura Gyms, which provide infrastructure for robot training models.
Yet while combining multiple sensory inputs could help robots handle tasks that cameras alone cannot, the approach poses a training challenge: collecting sufficient suitable data to teach models to understand and respond to those inputs.
“Most physical AI stacks are focused on VLA models, which learn from ‘seeing,’” said Rueben Scriven, senior research manager at industrial automation and robotics research market firm Interact Analysis. “What Neura is betting on is that models that can be trained on different sensory inputs will perform better.”
The approach could also complement Neura’s vertically integrated sensor stack, potentially giving the company an advantage over competitors.
However, Scriven questioned whether Neura could collect sufficient data to effectively train the model across so many sensory inputs.
“There’s already a limit on well-annotated video data, let alone multi-modal input data,” he said. “Therefore, the real question is whether data collection across its robotic gyms will be enough to train the models.”
Training robots beyond vision
Neura argues that additional sensory inputs are important for tasks in which visual information alone cannot reliably determine what is happening. When a robot opens a lock, only sound and touch confirm that it is really open, according to the company.
Related:Robots can't talk to each other yet -- that's a big AI bottleneck
The model’s memory function is intended to help robots maintain context as objects move out of view, and as the robot’s actions change its surroundings.
The company hasn’t yet disclosed how much the extra sensory inputs affect performance, or how much training data is needed to achieve reliable results.
Scarlett Evans is a freelance writer with a focus on emerging technologies and the minerals industry. Previously, she served as assistant editor at IoT World Today, where she specialized in robotics and smart city technologies. Scarlett also has a background in the mining and resources sector, with experience at Mine Australia, Mine Technology and Power Technology. She joined Informa in April 2022 before transitioning to freelance work.See more from Scarlett Evans
Latest NewsMore Latest NewsGenerative AIMicrosoft could hold an advantage with Copilot for LegalMicrosoft could hold an advantage with Copilot for LegalbyEsther ShittuOct 19, 20263 Min Read
Trending articlesSee moreGenerative AIMicrosoft could hold an advantage with Copilot for LegalMicrosoft could hold an advantage with Copilot for Legal
Oct 19, 2026RoboticsHow Boston is becoming a physical AI hubHow Boston is becoming a physical AI hub
Oct 19, 2026Latest podcasts
Generative AI
Musing about Muse’s new AI models, unruly DeepSeekOct 14, 2026
Generative AI
Reflection Beam aims U.S. open-weight AI model at Chinese rivalsOct 7, 2026
Generative AI
The context factor for AI agentsOct 7, 2026
Generative AI
The AI Summit New York 2026