Marco Hutter

ADAPT enables humanoid robots to seamlessly execute diverse motion skills in real-time based on text commands, revolutionizing interactive control.

Humanoid robots can now traverse complex 3D structures with remarkable agility and precision, completing intricate maneuvers in real-world trials.

Sparse rewards can now drive complex loco-manipulation skills, enabling robots to learn faster and perform better than traditional methods.

A groundbreaking dataset of 4D human motion sequences reveals how humanoid robots can effectively navigate complex terrains, setting a new standard for motion synthesis accuracy.

The SE(2) NavMesh captures over 50% more traversable area than classical navigation meshes, revolutionizing navigation for non-circular robots in complex environments.

Achieving a 50% reduction in Cost of Transport, this humanoid robot skates with unprecedented agility and balance, redefining locomotion strategies in robotics.

Sparse infrared proximity sensing enables quadrupedal robots to navigate complex terrains with unprecedented robustness, outperforming traditional perception methods.

ELMP slashes adaptation costs for motion planning by two orders of magnitude while boosting success rates in unseen environments to nearly 90%.

Real-world robots can now leverage photo-realistic digital twins constructed directly from RGB-D videos, eliminating the need for manual modeling.

Optimization-guided diffusion not only ensures feasibility in robot control tasks but also enhances task success rates by up to 23 percentage points without retraining the model.

Zero-shot sim-to-real transfer is achieved with a 16.7% reduction in force prediction error by aligning diverse tactile modalities in a shared latent space.

GAM revolutionizes robot policy learning by seamlessly integrating 3D geometric reasoning, outperforming traditional models in accuracy and efficiency.

Even near-perfect planning ability in LLMs doesn't ensure safety in robotic tasks, with the best models still generating dangerous plans almost 30% of the time.

Humanoid robots can now traverse complex terrains with whole-body coordination thanks to a novel framework that blends diffusion-based motion generation with robust RL-based tracking.

Legged robots can infer a partner's intent during collaborative transport directly from proprioceptive feedback, enabling robust cooperation without external sensors or payload tracking.