Temporal Logic Guided Motion Primitives for Complex Manipulation Tasks with User Preferences

TL;DR

This paper introduces a novel approach combining temporal logic with motion primitives to enable complex, preference-driven robotic manipulation tasks beyond simple point-to-point movements.

Contribution

It presents the PIBB-TL algorithm that integrates weighted truncated linear temporal logic into DMPs for complex task encoding and optimization.

Findings

Effective encoding of complex action sequences with user preferences

Successful simulation and experimental validation of the approach

Enhanced flexibility in robotic motion planning

Abstract

Dynamic movement primitives (DMPs) are a flexible trajectory learning scheme widely used in motion generation of robotic systems. However, existing DMP-based methods mainly focus on simple go-to-goal tasks. Motivated to handle tasks beyond point-to-point motion planning, this work presents temporal logic guided optimization of motion primitives, namely PIBB-TL algorithm, for complex manipulation tasks with user preferences. In particular, weighted truncated linear temporal logic (wTLTL) is incorporated in the PIBB-TL algorithm, which not only enables the encoding of complex tasks that involve a sequence of logically organized action plans with user preferences, but also provides a convenient and efficient means to design the cost function. The black-box optimization is then adapted to identify optimal shape parameters of DMPs to enable motion planning of robotic systems. The effectiveness of the PIBB-TL algorithm is demonstrated via simulation and experime