Instance-Aware Predictive Navigation in Multi-Agent Environments

Abstract

In this work, we aim to achieve efficient end-to-end learning of driving policies in dynamic multi-agent environments. Predicting and anticipating future events at the object level are critical for making informed driving decisions. We propose an Instance-Aware Predictive Control (IPC) approach, which forecasts interactions between agents as well as future scene structures. We adopt a novel multi-instance event prediction module to estimate the possible interaction among agents in the ego-centric view, conditioned on the selected action sequence of the ego-vehicle. To decide the action at each step, we seek the action sequence that can lead to safe future states based on the prediction module outputs by repeatedly sampling likely action sequences. We design a sequential action sampling strategy to better leverage predicted states on both scene-level and instance-level. Our method establishes a new state of the art in the challenging CARLA multi-agent driving simulation environments without expert demonstration, giving better explainability and sample efficiency.

References in corpus (8)

• Continuous control with deep reinforcement learning
• Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting
• Playing Atari with Deep Reinforcement Learning
• End to End Learning for Self-Driving Cars
• An Empirical Evaluation of Deep Learning on Highway Driving
• Virtual to Real Reinforcement Learning for Autonomous Driving
• Learning to Poke by Poking: Experiential Learning of Intuitive Physics
• Reinforcement Learning from Imperfect Demonstrations