Semi-Supervised Trajectory-Feedback Controller Synthesis for Signal Temporal Logic Specifications

TL;DR

This paper introduces a semi-supervised neural network controller synthesis method for robots that ensures compliance with spatio-temporal Signal Temporal Logic specifications while mimicking human-like behaviors, improving performance and efficiency.

Contribution

The work presents a novel semi-supervised, adversarial training approach for controller synthesis that incorporates imitation regularization to enhance naturalistic behaviors and specification satisfaction.

Findings

Outperforms state-of-the-art shooting methods in accuracy and speed.

Imitation regularization improves qualitative and quantitative performance.

Effective in complex, real-time control scenarios.

Abstract

There are spatio-temporal rules that dictate how robots should operate in complex environments, e.g., road rules govern how (self-driving) vehicles should behave on the road. However, seamlessly incorporating such rules into a robot control policy remains challenging especially for real-time applications. In this work, given a desired spatio-temporal specification expressed in the Signal Temporal Logic (STL) language, we propose a semi-supervised controller synthesis technique that is attuned to human-like behaviors while satisfying desired STL specifications. Offline, we synthesize a trajectory-feedback neural network controller via an adversarial training scheme that summarizes past spatio-temporal behaviors when computing controls, and then online, we perform gradient steps to improve specification satisfaction. Central to the offline phase is an imitation-based regularization component that fosters better policy exploration and helps induce naturalistic human behaviors. Our experiments demonstrate that having imitation-based regularization leads to higher qualitative and quantitative performance compared to optimizing an STL objective only as done in prior work. We demonstrate the efficacy of our approach with an illustrative case study and show that our proposed controller outperforms a state-of-the-art shooting method in both performance and computation time.