Logically Constrained Robotics Transformers for Enhanced Perception-Action Planning

TL;DR

This paper introduces a novel method integrating signal temporal logic constraints into autoregressive transformer models for robotic perception-action planning, significantly improving specification satisfaction in trajectory generation.

Contribution

It presents a new approach combining temporal logic with transformers for constrained planning and provides a trajectory dataset for pretraining and evaluation.

Findings

Achieves 74.3% higher specification satisfaction than baselines.

Demonstrates effective incorporation of temporal logic constraints into transformer models.

Provides a new dataset for trajectory pretraining and evaluation.

Abstract

With the advent of large foundation model based planning, there is a dire need to ensure their output aligns with the stakeholder's intent. When these models are deployed in the real world, the need for alignment is magnified due to the potential cost to life and infrastructure due to unexpected faliures. Temporal Logic specifications have long provided a way to constrain system behaviors and are a natural fit for these use cases. In this work, we propose a novel approach to factor in signal temporal logic specifications while using autoregressive transformer models for trajectory planning. We also provide a trajectory dataset for pretraining and evaluating foundation models. Our proposed technique acheives 74.3 % higher specification satisfaction over the baselines.