Boston Dynamics has revealed how its Atlas humanoid robot learned to lift and carry heavy industrial objects using reinforcement learning and large-scale simulation training.
In a newly released technical blog, the robotics company showed Atlas rotating its
torso 180 degrees, squatting to pick up a mini-fridge, and carrying it across a lab floor while adjusting to shifting weight inside the object. The company said the behavior was developed within weeks of Atlas’ public debut earlier this year.
The latest demo marks a shift from choreographed robot movements toward adaptable industrial behaviors designed for factories, warehouses, and construction sites. Boston Dynamics said Atlas is being developed as a “general purpose tool for physical work.”
Rather than relying mainly on cameras, the robot uses proprioception, or internal body awareness, to sense weight, balance, grip, and resistance while moving objects. The company said that approach allows Atlas to adapt in real time to unstable loads and changing conditions.
Boston Dynamics trained Atlas through reinforcement learning, where the robot repeatedly practiced the same lifting task in simulation under different conditions. The company varied factors such as object weight, floor friction, grip strength, and fridge positioning to force the robot to adapt.
“Atlas practiced the moves for millions of hours in simulations in parallel on Graphics Processing Units (GPUs),” the company said.
The process starts with a reference trajectory, which can be an animated movement or a teleoperated demonstration. Atlas is then rewarded for completing tasks correctly, such as maintaining grip on the object and staying balanced while external disturbances are introduced.
Once the behavior works reliably in simulation, engineers transfer it to the physical robot, test it, collect performance data, and refine the training again.
Boston Dynamics said one major advantage of the new Atlas platform is its reduced “sim-to-real gap,” a longstanding robotics challenge where behaviors trained in simulation fail in the physical world due to unpredictable variables such as friction, latency, or sensor noise.
The company said Atlas’ simplified hardware architecture makes accurate simulation easier. The humanoid uses only two actuator types across its body, while both arms and both legs are symmetrical in design.
The robot can also rotate joints continuously because engineers eliminated cables running across joints, reducing wear and allowing greater freedom of motion. Boston Dynamics said this helps Atlas perform movements that traditional humanoid robots struggle with.
The company added that Atlas was trained on 50-70 pound loads, but successfully moved a fridge weighing more than 100 pounds during testing.
“You cannot lift a fridge just by looking at it and using your hands,” Boston Dynamics wrote. “You have to prepare for it to anticipate the weight, lean into it, and let your body do the work.”
Boston Dynamics also linked Atlas’ athletic demonstrations, including handstands and backflips, to industrial use cases. According to the company, these movements help train balance, agility, slip recovery, and thermal endurance needed for harsh working environments.
Get the latest in engineering, tech, space & science - delivered daily to your inbox.
With over a decade-long career in journalism, Neetika Walter has worked with The Economic Times, ANI, and Hindustan Times, covering politics, business, technology, and the clean energy sector. Passionate about contemporary culture, books, poetry, and storytelling, she brings depth and insight to her writing. When she isn’t chasing stories, she’s likely lost in a book or enjoying the company of her dogs.
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。