Social Interactions for Autonomous Driving: A Review and Perspectives

Abstract

No human drives a car in a vacuum; she/he must negotiate with other road users to achieve their goals in social traffic scenes. A rational human driver can interact with other road users in a socially-compatible way through implicit communications to complete their driving tasks smoothly in interaction-intensive, safety-critical environments. This paper aims to review the existing approaches and theories to help understand and rethink the interactions among human drivers toward social autonomous driving. We take this survey to seek the answers to a series of fundamental questions: 1) What is social interaction in road traffic scenes? 2) How to measure and evaluate social interaction? 3) How to model and reveal the process of social interaction? 4) How do human drivers reach an implicit agreement and negotiate smoothly in social interaction? This paper reviews various approaches to modeling and learning the social interactions between human drivers, ranging from optimization theory and graphical models to social force theory and behavioral & cognitive science. We also highlight some new directions, critical challenges, and opening questions for future research.

arXiv comment183 pages, 36 figures

References in corpus (55)

• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• Social Force Model for Pedestrian Dynamics
• Traffic and Related Self-Driven Many-Particle Systems
• Active Particles in Complex and Crowded Environments
• The social dilemma of autonomous vehicles
• Physics of Microswimmers - Single Particle Motion and Collective Behavior
• On the Properties of Neural Machine Translation: Encoder-Decoder Approaches
• Deep Learning-based Vehicle Behaviour Prediction For Autonomous Driving Applications: A Review
• Human Motion Trajectory Prediction: A Survey
• Multi-Modal Trajectory Prediction of Surrounding Vehicles with Maneuver based LSTMs
• How would surround vehicles move? A Unified Framework for Maneuver Classification and Motion Prediction
• Collective behavior of interacting self-propelled particles
• INTERACTION Dataset: An INTERnational, Adversarial and Cooperative moTION Dataset in Interactive Driving Scenarios with Semantic Maps
• Bayesian Nonparametric Inference of Switching Linear Dynamical Systems
• TraPHic: Trajectory Prediction in Dense and Heterogeneous Traffic Using Weighted Interactions
• Game-Theoretic Multiagent Reinforcement Learning
• People construct simplified mental representations to plan
• Extracting Traffic Primitives Directly from Naturalistically Logged Data for Self-Driving Applications
• Occupancy Flow Fields for Motion Forecasting in Autonomous Driving
• Injecting Knowledge in Data-driven Vehicle Trajectory Predictors
• Social Attention for Autonomous Decision-Making in Dense Traffic
• Learning to Predict Vehicle Trajectories with Model-based Planning
• Interaction-aware Kalman Neural Networks for Trajectory Prediction
• Social-WaGDAT: Interaction-aware Trajectory Prediction via Wasserstein Graph Double-Attention Network
• On Social Interactions of Merging Behaviors at Highway On-Ramps in Congested Traffic
• People as Sensors: Imputing Maps from Human Actions
• Deep Interactive Motion Prediction and Planning: Playing Games with Motion Prediction Models
• Transferable and Adaptable Driving Behavior Prediction
• Uncovering Interpretable Internal States of Merging Tasks at Highway On-Ramps for Autonomous Driving Decision-Making
• Scenario-Transferable Semantic Graph Reasoning for Interaction-Aware Probabilistic Prediction
• Posetal Games: Efficiency, Existence, and Refinement of Equilibria in Games with Prioritized Metrics
• Hierarchical Adaptable and Transferable Networks (HATN) for Driving Behavior Prediction
• Potential Field: Interpretable and Unified Representation for Trajectory Prediction
• Multimodal Trajectory Prediction via Topological Invariance for Navigation at Uncontrolled Intersections
• A General Framework of Learning Multi-Vehicle Interaction Patterns from Videos
• Driving Style Encoder: Situational Reward Adaptation for General-Purpose Planning in Automated Driving
• Implicit Multiagent Coordination at Unsignalized Intersections via Multimodal Inference Enabled by Topological Braids
• Uncertainty estimation for Cross-dataset performance in Trajectory prediction
• Models of human behavior for human-robot interaction and automated driving: How accurate do the models of human behavior need to be?
• SFMGNet: A Physics-based Neural Network To Predict Pedestrian Trajectories
• Sub-Goal Social Force Model for Collective Pedestrian Motion Under Vehicle Influence
• GAMMA: A General Agent Motion Model for Autonomous Driving
• Simulating Autonomous Driving in Massive Mixed Urban Traffic
• Active Altruism Learning and Information Sufficiency for Autonomous Driving
• Online Adaptation of Neural Network Models by Modified Extended Kalman Filter for Customizable and Transferable Driving Behavior Prediction
• Moving efficiently through a crowd: a nature inspired traffic rule
• Interaction-Aware Trajectory Prediction and Planning for Autonomous Vehicles in Forced Merge Scenarios
• Deep Social Force
• An Introduction to Multi-Agent Reinforcement Learning and Review of its Application to Autonomous Mobility
• Control-Aware Prediction Objectives for Autonomous Driving
• Social Coordination and Altruism in Autonomous Driving
• Heterogeneous-Agent Trajectory Forecasting Incorporating Class Uncertainty
• Interventional Behavior Prediction: Avoiding Overly Confident Anticipation in Interactive Prediction
• Modeling Human Driver Interactions Using an Infinite Policy Space Through Gaussian Processes
• Trajectory Prediction with Graph-based Dual-scale Context Fusion

Cited by in corpus (6)

• From SLAM to Situational Awareness: Challenges and Survey
• Bayesian Calibration of the Intelligent Driver Model
• Vision-based Multi-future Trajectory Prediction: A Survey
• Disentangled Neural Relational Inference for Interpretable Motion Prediction
• How Bad is Selfish Driving? Bounding the Inefficiency of Equilibria in Urban Driving Games
• Towards Developing Socially Compliant Automated Vehicles: Advances, Expert Insights, and A Conceptual Framework