TorqueFlow powers robotic operations in logistics and warehouse environments. By reasoning about spatial layouts, object relationships, and deformable materials, it enables reliable trailer unloading, mixed-SKU sorting, kitting, and deformable packing.

Ashutosh Saxena, Founder & CEO of TorqueAGI, has dedicated decades to merging research and entrepreneurship in AI. His current focus is on enabling robots to perform meaningful tasks in the real world.

In this Humanoids Summit interview, Ian Khan speaks with Ashutosh Saxena, Founder & CEO at TorqueAGI, about the innovations and leadership shaping humanoid robotics and AI solutions. Ashutosh shares insights into entrepreneurial strategy, scaling cutting-edge robotics technologies, and translating research into practical, real-world applications.

In this episode of the Control Alt Podcast, we sit down with AI pioneer Dr. Ashutosh Saxena, Founder & CEO of TorqueAGI. Dr. Saxena, who has worked with the likes of Andrew Ng at Stanford University, is at the forefront of the robotics revolution, building robots that can think and do things autonomously.

TorqueFlow classifies bags and selects grasp poses simultaneously. The orange overlay evaluates positions, ensuring informed decisions. Designed for mixed SKU pick-and-sort, it tackles logistics challenges with seamless object recognition and classification.

Dr. Ashutosh Saxena, Founder and CEO of TorqueAGI, takes the stage at NVIDIA GTC 2026 to present how TorqueAGI and NVIDIA technology work together to bring physical AI to enterprise-grade robotics.

Every warehouse is different. Conventional AI fails. Physical AI reasons. Robotic failure compounds but when logistics works, it unlocks global systems: freight, medicine, e-commerce. TorqueAGI is building that frontier.

Making ice cream is easy for humans. For robots, it exposes a hard problem. Long-horizon tasks require memory, planning, and coordination across many steps, not just perception and control.

Cross-embodiment learning shifts robotics from memorizing robot-specific datasets to learning transferable physical abstractions. The result: orders of magnitude less data and far faster deployment across different machines.

This video shows TorqueAGI’s edge native foundation model running fully on device, operating in real time with no data sent off platform. The model runs live, observing the environment, reasoning over it, and triggering behavior under real world constraints

Cross-embodiment learning lets robots build on each other’s experience instead of starting over every time, unlocking their true potential. No retraining. No custom scripting. This was the idea behind Robobrain and the foundation that TorqueAGI is built on.

At TorqueAGI, we are building the Physical AI foundation model that enables this structured decision-making. It lets humanoids handle complex workflows in warehouses, manufacturing, and logistics in the real world today.

VLAs can generalize in the cloud. Robots need real-time on the edge. The only architecture that works puts the entire intelligence pipeline on the GPU. Three steps make this possible.