Social Attention for Autonomous Decision-Making in Dense Traffic
arXiv:1911.12250
Abstract
We study the design of learning architectures for behavioural planning in a dense traffic setting. Such architectures should deal with a varying number of nearby vehicles, be invariant to the ordering chosen to describe them, while staying accurate and compact. We observe that the two most popular representations in the literature do not fit these criteria, and perform badly on an complex negotiation task. We propose an attention-based architecture that satisfies all these properties and explicitly accounts for the existing interactions between the traffic participants. We show that this architecture leads to significant performance gains, and is able to capture interactions patterns that can be visualised and qualitatively interpreted. Videos and code are available at https://eleurent.github.io/social-attention/.
References in corpus (7)
- Congested Traffic States in Empirical Observations and Microscopic Simulations
- End to End Learning for Self-Driving Cars
- Recurrent World Models Facilitate Policy Evolution
- End-to-End Deep Learning for Steering Autonomous Vehicles Considering Temporal Dependencies
- Deep Imitative Models for Flexible Inference, Planning, and Control
- DeepTraffic: Crowdsourced Hyperparameter Tuning of Deep Reinforcement Learning Systems for Multi-Agent Dense Traffic Navigation
- Elements of Effective Deep Reinforcement Learning towards Tactical Driving Decision Making
Cited by in corpus (10)
- Social Interactions for Autonomous Driving: A Review and Perspectives
- Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecasting
- Decision-making at Unsignalized Intersection for Autonomous Vehicles: Left-turn Maneuver with Deep Reinforcement Learning
- Decentralized policy learning with partial observation and mechanical constraints for multiperson modeling
- StylePredict: Machine Theory of Mind for Human Driver Behavior From Trajectories
- I'm sorry Dave, I'm afraid I can't do that, Deep Q-learning from forbidden action
- Scalable Multi-modal Model Predictive Control via Duality-based Interaction Predictions
- MIDAS: Multi-agent Interaction-aware Decision-making with Adaptive Strategies for Urban Autonomous Navigation
- Learning interaction rules from multi-animal trajectories via augmented behavioral models
- Spatially and Seamlessly Hierarchical Reinforcement Learning for State Space and Policy space in Autonomous Driving