Compact quadrupedal robots are proving increasingly suitable for deployment in real-world scenarios. Their smaller size fosters easy integration into human environments. Nevertheless, real-time locomotion on uneven terrains remains challenging, particularly due to the high computational demands of terrain perception. This paper presents a robust reinforcement learning-based exteroceptive locomotion controller for resource-constrained small-scale quadrupeds in challenging terrains, which exploits real-time elevation mapping, supported by a careful depth sensor selection. We concurrently train both a policy and a state estimator, which together provide an odometry source for elevation mapping, optionally fused with visual-inertial odometry (VIO). We demonstrate the importance of positioning an additional time-of-flight sensor for maintaining robustness even without VIO, thus having the potential to free up computational resources. We experimentally demonstrate that the proposed controller can flawlessly traverse steps up to 17.5 cm in height and achieve an 80% success rate on 22.5 cm steps, both with and without VIO. The proposed controller also achieves accurate forward and yaw velocity tracking of up to 1.0 m/s and 1.5 rad/s respectively. We open-source our training code at github.com/ETH-PBL/elmap-rl-controller.

翻译：紧凑型四足机器人正日益展现出在实际场景中部署的适用性。其较小的尺寸有利于融入人类生活环境。然而，在不平整地形上的实时运动仍然具有挑战性，这尤其源于地形感知的高计算需求。本文提出一种面向资源受限小型四足机器人的鲁棒强化学习外感知运动控制器，适用于复杂地形环境。该控制器通过精心的深度传感器选型，利用实时高程地图实现地形感知。我们同步训练策略网络与状态估计器，二者共同为高程地图构建提供里程计数据源，并可选择性地与视觉惯性里程计（VIO）融合。实验证明，即使在不使用VIO的情况下，通过合理配置额外飞行时间传感器仍能保持系统鲁棒性，从而有望释放计算资源。实验结果表明：无论是否使用VIO，所提出的控制器均能无瑕疵地跨越高度达17.5厘米的台阶，并在22.5厘米台阶上实现80%的成功率。该控制器还能实现高达1.0米/秒的前向速度跟踪精度和1.5弧度/秒的偏航角速度跟踪精度。我们在github.com/ETH-PBL/elmap-rl-controller开源了训练代码。