Self-Supervised Traffic Advisors: Distributed, Multi-view Traffic Prediction for Smart Cities

Abstract

Connected autonomous vehicles (CAVs) promise to enhance safety, efficiency, and sustainability in urban transportation. However, this is contingent upon a CAV correctly predicting the motion of surrounding agents and planning its own motion safely. Doing so is challenging in complex urban environments due to frequent occlusions and interactions among many agents. One solution is to leverage smart infrastructure to augment a CAV's situational awareness; the present work leverages a recently-proposed "Self-Supervised Traffic Advisor" (SSTA) framework of smart sensors that teach themselves to generate and broadcast useful video predictions of road users. In this work, SSTA predictions are modified to predict future occupancy instead of raw video, which reduces the data footprint of broadcast predictions. The resulting predictions are used within a planning framework, demonstrating that this design can effectively aid CAV motion planning. A variety of numerical experiments study the key factors that make SSTA outputs useful for practical CAV planning in crowded urban environments.

A Survey of Reasoning with Foundation Models

“…Reasoning within the domain of autonomous driving spans across perception (Li et al, 2023e,l;Sun et al, 2022bSun et al, , 2023c, safety (Zhou et al, 2023c), explainability (Echterhoff et al, 2023;Sha et al, 2023;Sun et al, 2021;Huang et al, 2021b) and system level (Chen et al, 2023f). Chen et al (2023f) propose the frontiers and challenges for end-to-end autonomous driving, where logical reasoning with LLMs could have substantial impacts on different driving scenarios.…”