8 papers
Shape Your Body: Value Gradients for Multi-Embodiment Robot Design
Nico Bohlinger, Jan Peters
We propose to turn generalist multi-embodiment value functions into reusable models for robot design. Instead of running a new reinforcement learning co-design loop for each robot,…
Active Embodiment Identification with Reinforcement Learning for Legged Robots
Nico Bohlinger, Jan Peters
We present an active embodiment identification method for legged robots that jointly learns information-seeking behavior and explicit embodiment prediction. Using a history-augment…
Evaluation of an Actuated Spine in Agile Quadruped Locomotion
Nico Bohlinger, Piotr Kicki, Davide Tateo +2
The spine plays a crucial role in the dynamic locomotion of quadrupedal animals, improving the stability, speed, and efficiency of their gait, especially for fast-paced and highly…
Bridge the Gap: Enhancing Quadruped Locomotion with Vertical Ground Perturbations
Maximilian Stasica, Arne Bick, Nico Bohlinger +5
Legged robots, particularly quadrupeds, excel at navigating rough terrains, yet their performance under vertical ground perturbations, such as those from oscillating surfaces, rema…
Multi-Embodiment Locomotion at Scale with extreme Embodiment Randomization
Nico Bohlinger, Jan Peters
We present a single, general locomotion policy trained on a diverse collection of 50 legged robots. By combining an improved embodiment-aware architecture (URMAv2) with a performan…
Gait in Eight: Efficient On-Robot Learning for Omnidirectional Quadruped Locomotion
Nico Bohlinger, Jonathan Kinzel, Daniel Palenicek +2
On-robot Reinforcement Learning is a promising approach to train embodiment-aware policies for legged robots. However, the computational constraints of real-time learning on robots…