A Data-Driven Approach to Synthesizing Dynamics-Aware Trajectories for Underactuated Robotic Systems

TL;DR

This paper introduces a data-driven, dynamics-aware trajectory generation method for underactuated robots, improving planning and control by learning from system rollouts and handling real-world uncertainties.

Contribution

It proposes a novel augmented Lagrangian reformulation for trajectory optimization that incorporates a learnable tracking penalty, enhancing dynamic feasibility and computational efficiency.

Findings

Improved trajectory planning and control in simulation and hardware.

Effective handling of the sim-to-real gap without additional training.

Significant reduction in computation time and increased dynamic feasibility.

Abstract

We consider joint trajectory generation and tracking control for under-actuated robotic systems. A common solution is to use a layered control architecture, where the top layer uses a simplified model of system dynamics for trajectory generation, and the low layer ensures approximate tracking of this trajectory via feedback control. While such layered control architectures are standard and work well in practice, selecting the simplified model used for trajectory generation typically relies on engineering intuition and experience. In this paper, we propose an alternative data-driven approach to dynamics-aware trajectory generation. We show that a suitable augmented Lagrangian reformulation of a global nonlinear optimal control problem results in a layered decomposition of the overall problem into trajectory planning and feedback control layers. Crucially, the resulting trajectory optimization is dynamics-aware, in that, it is modified with a tracking penalty regularizer encoding the dynamic feasibility of the generated trajectory. We show that this tracking penalty regularizer can be learned from system rollouts for independently-designed low layer feedback control policies, and instantiate our framework in the context of a unicycle and a quadrotor control problem in simulation. Further, we show that our approach handles the sim-to-real gap through experiments on the quadrotor hardware platform without any additional training. For both the synthetic unicycle example and the quadrotor system, our framework shows significant improvements in both computation time and dynamic feasibility in simulation and hardware experiments.