Visually-guided motion planning for autonomous driving from interactive demonstrations. (November 2022)

• Record Type: Journal Article
• Authors: Pérez-Dattari, Rodrigo; Brito, Bruno; de Groot, Oscar; Kober, Jens; Alonso-Mora, Javier
• Is Part Of: Engineering applications of artificial intelligence. Volume 116(2022)
• Publication Date: 2022-11
• Subjects: Interactive Imitation Learning -- Model Predictive Control -- Autonomous driving -- Deep learning -- Motion planning -- Human in the loop; Engineering -- Data processing -- Periodicals; Artificial intelligence -- Periodicals; Expert systems (Computer science) -- Periodicals; Ingénierie -- Informatique -- Périodiques; Intelligence artificielle -- Périodiques; Systèmes experts (Informatique) -- Périodiques; Artificial intelligence; Engineering -- Data processing; Expert systems (Computer science); Periodicals; 620.00285
• DOI: 10.1016/j.engappai.2022.105277
• Languages: English
• ISSNs: 0952-1976

Abstract

Abstract: The successful integration of autonomous robots in real-world environments strongly depends on their ability to reason from context and take socially acceptable actions. Current autonomous navigation systems mainly rely on geometric information and hard-coded rules to induce safe and socially compliant behaviors. Yet, in unstructured urban scenarios these approaches can become costly and suboptimal. In this paper, we introduce a motion planning framework consisting of two components: a data-driven policy that uses visual inputs and human feedback to generate socially compliant driving behaviors (encoded by high-level decision variables), and a local trajectory optimization method that executes these behaviors (ensuring safety). In particular, we employ Interactive Imitation Learning to jointly train the policy with the local planner, a Model Predictive Controller (MPC), which results in safe and human-like driving behaviors. Our approach is validated in realistic simulated urban scenarios. Qualitative results show the similarity of the learned behaviors with human driving. Furthermore, navigation performance is substantially improved in terms of safety, i.e., number of collisions, as compared to prior trajectory optimization frameworks, and in terms of data-efficiency as compared to prior learning-based frameworks, broadening the operational domain of MPC to more realistic autonomous driving scenarios. Highlights: Interactive Imitation Learning can induce human-like driving behavior in optimization-based trajectory planners. Trajectory planners are safer and more socially-compliant when they resemble human-like driving behavior. Interactive Imitation Learning allows to learn human-like driving behaviors in few hours of human teaching.