Abstract
Terrain-aware locomotion has become an emerging topic in legged robotics. However, it is hard to generate challenging and realistic terrains in simulation, which limits the way researchers evaluate their locomotion policies. In this paper, we prototype the generation of a terrain dataset via terrain authoring and active learning, and the learned samplers can stably generate diverse high-quality terrains. Hopefully, the generated dataset can make a terrain-robustness benchmark for legged locomotion. The dataset and the code implementation are released at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2208.07681