Published on Wed Nov 27 2019

Social Attention for Autonomous Decision-Making in Dense Traffic

Edouard Leurent, Jean Mercat

We study the design of learning architectures for behavioural planning in a dense traffic setting. We propose an attention-based architecture that explicitly accounts for the existing interactions between the traffic participants. This architecture is able to capture interactions that can be visualised and qualitatively interpreted.

0
0
0
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/.

Mon Aug 17 2020
Machine Learning
MIDAS: Multi-agent Interaction-aware Decision-making with Adaptive Strategies for Urban Autonomous Navigation
Autonomous navigation in crowded, complex urban environments requires interacting with other agents on the road. A common solution to this problem is to use a prediction model to guess the likely future actions of other agents. This leads to overly conservative plans because it does not explicitly model the mutual influence of the
0
0
0
Tue Jan 28 2020
Artificial Intelligence
Towards Learning Multi-agent Negotiations via Self-Play
Self-play can create progressively more diverse environments, leading to the learning of sophisticated and robust multi-agent policies. We demonstrate this in a challenging simulation of merging traffic. We find that through self-play, our policies automatically learn interestingbehaviors such as defensive driving, overtaking, yielding.
0
0
0
Fri Feb 12 2021
Artificial Intelligence
SCOUT: Socially-COnsistent and UndersTandable Graph Attention Network for Trajectory Prediction of Vehicles and VRUs
0
0
0
Sun Jan 17 2021
Artificial Intelligence
TrafficSim: Learning to Simulate Realistic Multi-Agent Behaviors
Existing simulation environments rely on heuristic-based models that directly encode traffic rules. In contrast, we leverage real-world data to learn directly from human demonstration. We show that TrafficSim generates significantly more realistic and diverse traffic scenarios.
1
0
2
Fri Feb 26 2021
Artificial Intelligence
Scalable Multiagent Driving Policies For Reducing Traffic Congestion
Traffic congestion is a major challenge in modern urban settings. Past research has shown that in small scale mixed traffic scenarios with both AVs and human-driven vehicles, a small fraction of AVs can mitigate congestion. In this paper, we scale up existing approaches and develop new multiagent driving policies.
0
0
0
Mon Sep 30 2019
Artificial Intelligence
Dynamic Interaction-Aware Scene Understanding for Reinforcement Learning in Autonomous Driving
The common pipeline in autonomous driving systems is highly modular and includes a perception component which extracts lists of surrounding objects. In this case, leveraging the benefits of deep reinforcement learning for high-level decision making requires special architectures to deal with multiple variable-length sequences.
0
0
0