Shadow Program Inversion with Differentiable Planning: A Framework for Unified Robot Program Parameter and Trajectory Optimization

TL;DR

This paper introduces SPI-DP, a differentiable planning framework that enables joint optimization of robot program parameters and trajectories, improving task efficiency and safety in practical applications.

Contribution

The paper presents DGPMP2-ND, a differentiable collision-free motion planner integrated into SPI-DP for unified robot program and trajectory optimization.

Findings

Effective optimization of robot programs with collision constraints.

Improved cycle time and smoothness in robot trajectories.

Enhanced human interpretability and modifiability of programs.

Abstract

This paper presents SPI-DP, a novel first-order optimizer capable of optimizing robot programs with respect to both high-level task objectives and motion-level constraints. To that end, we introduce DGPMP2-ND, a differentiable collision-free motion planner for serial N-DoF kinematics, and integrate it into an iterative, gradient-based optimization approach for generic, parameterized robot program representations. SPI-DP allows first-order optimization of planned trajectories and program parameters with respect to objectives such as cycle time or smoothness subject to e.g. collision constraints, while enabling humans to understand, modify or even certify the optimized programs. We provide a comprehensive evaluation on two practical household and industrial applications.