NaviGAN: A Generative Approach for Socially Compliant Navigation
This work addresses the challenge of socially compliant navigation for robots in crowded environments, representing an incremental improvement by combining existing optimization aspects.
The paper tackles the problem of robots navigating in human crowds by jointly optimizing for both comfort and naturalness, proposing NaviGAN, a generative navigation algorithm that learns to generate socially compliant paths through adversarial training, with experiments on multiple datasets and real-world robot tests demonstrating its effectiveness.
Robots navigating in human crowds need to optimize their paths not only for their task performance but also for their compliance to social norms. One of the key challenges in this context is the lack of standard metrics for evaluating and optimizing a socially compliant behavior. Existing works in social navigation can be grouped according to the differences in their optimization objectives. For instance, the reinforcement learning approaches tend to optimize on the \textit{comfort} aspect of the socially compliant navigation, whereas the inverse reinforcement learning approaches are designed to achieve \textit{natural} behavior. In this paper, we propose NaviGAN, a generative navigation algorithm that jointly optimizes both of the \textit{comfort} and \textit{naturalness} aspects. Our approach is designed as an adversarial training framework that can learn to generate a navigation path that is both optimized for achieving a goal and for complying with latent social rules. A set of experiments has been carried out on multiple datasets to demonstrate the strengths of the proposed approach quantitatively. We also perform extensive experiments using a physical robot in a real-world environment to qualitatively evaluate the trained social navigation behavior. The video recordings of the robot experiments can be found in the link: https://youtu.be/61blDymjCpw.