Learning Perceptual Locomotion on Uneven Terrains Using Sparse Visual Observations

Acero, Fernando; Yuan, Kai; Li, Zhibin

doi:10.1109/lra.2022.3188108

Cited by 4 publications

(1 citation statement)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It fuses multiple NNs into one according to a gating network’s output to produce adaptive behaviors in response to changing situations. Meanwhile, expanding information sources with perceptual sensing such as heightmap scanning [ 18 ] and introducing latent encoders are also means to enhance trained policies. ANYmal robot conquered a series of challenging terrains with privilege learning and latent encoder [ 19 , 20 ].…”

Section: Introductionmentioning

confidence: 99%

Hybrid Bipedal Locomotion Based on Reinforcement Learning and Heuristics

et al. 2022

View full text Add to dashboard Cite

Locomotion control has long been vital to legged robots. Agile locomotion can be implemented through either model-based controller or reinforcement learning. It is proven that robust controllers can be obtained through model-based methods and learning-based policies have advantages in generalization. This paper proposed a hybrid framework of locomotion controller that combines deep reinforcement learning and simple heuristic policy and assigns them to different activation phases, which provides guidance for adaptive training without producing conflicts between heuristic knowledge and learned policies. The training in simulation follows a step-by-step stochastic curriculum to guarantee success. Domain randomization during training and assistive extra feedback loops on real robot are also adopted to smooth the transition to the real world. Comparison experiments are carried out on both simulated and real Wukong-IV humanoid robots, and the proposed hybrid approach matches the canonical end-to-end approaches with higher rate of success, faster converging speed, and 60% less tracking error in velocity tracking tasks.

show abstract

Section: Introductionmentioning

confidence: 99%