Combining the agility of legged locomotion with the capabilities of manipulation, loco-manipulation platforms have the potential to perform complex tasks in real-world applications. To this end, state-of-the-art quadrupeds with attached manipulators, such as the Boston Dynamics Spot, have emerged to provide a capable and robust platform. However, both the complexity of loco-manipulation control, as well as the black-box nature of commercial platforms pose challenges for developing accurate dynamics models and control policies. We address these challenges by developing a hand-crafted kinematic model for a quadruped-with-arm platform and, together with recent advances in Bayesian Neural Network (BNN)-based dynamics learning using physical priors, efficiently learn an accurate dynamics model from data. We then derive control policies for loco-manipulation via model-based reinforcement learning (RL). We demonstrate the effectiveness of this approach on hardware using the Boston Dynamics Spot with a manipulator, accurately performing dynamic end-effector trajectory tracking even in low data regimes.

翻译：结合了腿部运动的敏捷性与操作能力，移动操作平台有潜力在现实应用中执行复杂任务。为此，配备了机械臂的先进四足机器人（如波士顿动力公司的Spot）已成为一种能力强且鲁棒的平台。然而，移动操作控制的复杂性以及商业平台的黑盒特性，为开发精确的动力学模型和控制策略带来了挑战。我们通过为带机械臂的四足平台开发手工构建的运动学模型，并结合基于贝叶斯神经网络（BNN）的、利用物理先验的动力学学习最新进展，从数据中高效学习精确的动力学模型，从而应对这些挑战。随后，我们通过基于模型的强化学习（RL）推导出移动操作的控制策略。我们在配备机械臂的波士顿动力Spot机器人硬件上验证了该方法的有效性，即使在低数据量情况下也能精确执行动态末端执行器轨迹跟踪。