Formal Methods in Robot Policy Learning and Verification: A Survey on Current Techniques and Future Directions

TL;DR

This survey reviews recent advances in formal methods applied to robot policy learning and verification, emphasizing techniques that improve safety and correctness amidst increasing complexity and deep learning adoption.

Contribution

It provides a comprehensive overview of formal methods in robot learning, comparing techniques, and discussing future challenges and directions.

Findings

Highlighting formal methods that enhance robot safety and correctness.

Comparison of scalability and expressiveness of different techniques.

Identification of remaining obstacles and promising future research directions.

Abstract

As hardware and software systems have grown in complexity, formal methods have been indispensable tools for rigorously specifying acceptable behaviors, synthesizing programs to meet these specifications, and validating the correctness of existing programs. In the field of robotics, a similar trend of rising complexity has emerged, driven in large part by the adoption of deep learning. While this shift has enabled the development of highly performant robot policies, their implementation as deep neural networks has posed challenges to traditional formal analysis, leading to models that are inflexible, fragile, and difficult to interpret. In response, the robotics community has introduced new formal and semi-formal methods to support the precise specification of complex objectives, guide the learning process to achieve them, and enable the verification of learned policies against them. In this survey, we provide a comprehensive overview of how formal methods have been used in recent robot learning research. We organize our discussion around two pillars: policy learning and policy verification. For both, we highlight representative techniques, compare their scalability and expressiveness, and summarize how they contribute to meaningfully improving realistic robot safety and correctness. We conclude with a discussion of remaining obstacles for achieving that goal and promising directions for advancing formal methods in robot learning.