Bipedal robot with large wheels learns to roll over rough terrain
RAIWAY: A Large-Wheeled Bipedal Robot with Contact-Informed Blind Locomotion
Robotics
Summary
Moving on rough terrain is tricky because wheels interact with ground in complex ways that are hard to measure directly. The authors created a robot with big wheels and taught it to understand these hidden contact details by learning from simulations. The robot then uses its own sensors to figure out how to move smoothly without needing special contact sensors. It can climb slopes, walk on gravel, and even go up outdoor stairs with steps as high as 15 cm. This new control method works better than previous ones in tough indoor and outdoor places.
What this means in practice
- •For field robotics engineers: Develop robots that can roll and walk reliably over rough, uneven natural terrain without specialized ground sensors.
- •For robotics product developers: Create outdoor inspection or delivery robots capable of climbing stairs and traversing complex urban environments using internal sensing only.$Commercial implications: Enables the design of wheeled bipedal robots for outdoor tasks requiring stair climbing and rough terrain navigation, otherwise not commercially feasible.
Authors
Kyungmin Nam, Jiseong Lee, Donghyuk Choi, Jeongsoo Park, Woojin Kim, Jemin Hwangbo
Abstract
We present RAIWAY, an in-house wheeled bipedal robot with 20-inch wheels, together with a contact-informed control approach for rolling locomotion across irregular and discontinuous terrain. Such locomotion is fundamentally contact-dominated, governed by local wheel--terrain interaction that is impractical to instrument directly and depends on more than terrain geometry alone. The proposed framework exploits the contact information available in simulation, distilling multi-contact events into a latent representation. At deployment, the controller infers this representation online from proprioception, requiring no contact sensing. In real-world experiments, the proposed system traverses diverse environments including steep slopes, gravel beds, studded surfaces, and rocky terrain, and demonstrates continuous ascent on the tested outdoor staircases with riser heights up to 15~cm. On our platform, the proposed controller further outperforms baselines without the contact-informed mechanism across challenging indoor and outdoor settings. The video can be found at https://youtu.be/Ch0divLg64w.