How would surround vehicles move? A Unified Framework for Maneuver Classification and Motion Prediction

Abstract

Reliable prediction of surround vehicle motion is a critical requirement for path planning for autonomous vehicles. In this paper we propose a unified framework for surround vehicle maneuver classification and motion prediction that exploits multiple cues, namely, the estimated motion of vehicles, an understanding of typical motion patterns of freeway traffic and inter-vehicle interaction. We report our results in terms of maneuver classification accuracy and mean and median absolute error of predicted trajectories against the ground truth for real traffic data collected using vehicle mounted sensors on freeways. An ablative analysis is performed to analyze the relative importance of each cue for trajectory prediction. Additionally, an analysis of execution time for the components of the framework is presented. Finally, we present multiple case studies analyzing the outputs of our model for complex traffic scenarios

Accepted for publication in IEEE transactions on Intelligent Vehicles

References in corpus (2)

• No Blind Spots: Full-Surround Multi-Object Tracking for Autonomous Vehicles using Cameras & LiDARs
• A Multimodal, Full-Surround Vehicular Testbed for Naturalistic Studies and Benchmarking: Design, Calibration and Deployment

Cited by in corpus (45)

• Lidar for Autonomous Driving: The principles, challenges, and trends for automotive lidar and perception systems
• Multi-Modal Trajectory Prediction of Surrounding Vehicles with Maneuver based LSTMs
• Graph-Based Spatial-Temporal Convolutional Network for Vehicle Trajectory Prediction in Autonomous Driving
• TraPHic: Trajectory Prediction in Dense and Heterogeneous Traffic Using Weighted Interactions
• A Review of Tracking, Prediction and Decision Making Methods for Autonomous Driving
• Social Interactions for Autonomous Driving: A Review and Perspectives
• Modeling Human Driving Behavior through Generative Adversarial Imitation Learning
• GRIP++: Enhanced Graph-based Interaction-aware Trajectory Prediction for Autonomous Driving
• CSCNet: Contextual Semantic Consistency Network for Trajectory Prediction in Crowded Spaces
• Spatiotemporal Learning of Multivehicle Interaction Patterns in Lane-Change Scenarios
• Interaction-aware Kalman Neural Networks for Trajectory Prediction
• Clustering of Driving Encounter Scenarios Using Connected Vehicle Trajectories
• Social-WaGDAT: Interaction-aware Trajectory Prediction via Wasserstein Graph Double-Attention Network
• Teaching Vehicles to Anticipate: A Systematic Study on Probabilistic Behavior Prediction Using Large Data Sets
• Trajectory Prediction for Autonomous Driving: Progress, Limitations, and Future Directions
• TrackMPNN: A Message Passing Graph Neural Architecture for Multi-Object Tracking
• What-If Motion Prediction for Autonomous Driving
• MixNet: Structured Deep Neural Motion Prediction for Autonomous Racing
• Literature Review on Maneuver-Based Scenario Description for Automated Driving Simulations
• TPNet: Trajectory Proposal Network for Motion Prediction
• Uncertainty-Aware Driver Trajectory Prediction at Urban Intersections
• A Software Architecture for Autonomous Vehicles: Team LRM-B Entry in the First CARLA Autonomous Driving Challenge
• Interaction-aware Multi-agent Tracking and Probabilistic Behavior Prediction via Adversarial Learning
• Decoder Fusion RNN: Context and Interaction Aware Decoders for Trajectory Prediction
• GISNet: Graph-Based Information Sharing Network For Vehicle Trajectory Prediction
• Predicting Vehicle Behaviors Over An Extended Horizon Using Behavior Interaction Network
• A Fog Computing Framework for Autonomous Driving Assist: Architecture, Experiments, and Challenges
• Hierarchical Motion Encoder-Decoder Network for Trajectory Forecasting
• Congestion-aware Multi-agent Trajectory Prediction for Collision Avoidance
• Trajectory Prediction with Latent Belief Energy-Based Model
• Road obstacles positional and dynamic features extraction combining object detection, stereo disparity maps and optical flow data
• Modeling Multi-Vehicle Interaction Scenarios Using Gaussian Random Field
• Spatio-Temporal Graph Dual-Attention Network for Multi-Agent Prediction and Tracking
• Lifelong Vehicle Trajectory Prediction Framework Based on Generative Replay
• MSN: Multi-Style Network for Trajectory Prediction
• Quality-Aware Broadcasting Strategies for Position Estimation in VANETs
• BGM: Building a Dynamic Guidance Map without Visual Images for Trajectory Prediction
• Multi-Agent Tensor Fusion for Contextual Trajectory Prediction
• Building Real-time Awareness of Out-of-distribution in Trajectory Prediction for Autonomous Vehicles
• UST: Unifying Spatio-Temporal Context for Trajectory Prediction in Autonomous Driving
• Trajectory Generation by Chance Constrained Nonlinear MPC with Probabilistic Prediction
• On-Demand Trajectory Predictions for Interaction Aware Highway Driving
• Spatio-Temporal Look-Ahead Trajectory Prediction using Memory Neural Network
• A Taxonomy and Review of Algorithms for Modeling and Predicting Human Driver Behavior
• A LiDAR Assisted Control Module with High Precision in Parking Scenarios for Autonomous Driving Vehicle