TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Papers/BiTraP: Bi-directional Pedestrian Trajectory Prediction wi...

BiTraP: Bi-directional Pedestrian Trajectory Prediction with Multi-modal Goal Estimation

Yu Yao, Ella Atkins, Matthew Johnson-Roberson, Ram Vasudevan, Xiaoxiao Du

2020-07-29Pedestrian Trajectory PredictionAutonomous DrivingPredictionRobot NavigationCollision AvoidanceMulti-future Trajectory PredictionTrajectory Prediction
PaperPDFCode

Abstract

Pedestrian trajectory prediction is an essential task in robotic applications such as autonomous driving and robot navigation. State-of-the-art trajectory predictors use a conditional variational autoencoder (CVAE) with recurrent neural networks (RNNs) to encode observed trajectories and decode multi-modal future trajectories. This process can suffer from accumulated errors over long prediction horizons (>=2 seconds). This paper presents BiTraP, a goal-conditioned bi-directional multi-modal trajectory prediction method based on the CVAE. BiTraP estimates the goal (end-point) of trajectories and introduces a novel bi-directional decoder to improve longer-term trajectory prediction accuracy. Extensive experiments show that BiTraP generalizes to both first-person view (FPV) and bird's-eye view (BEV) scenarios and outperforms state-of-the-art results by ~10-50%. We also show that different choices of non-parametric versus parametric target models in the CVAE directly influence the predicted multi-modal trajectory distributions. These results provide guidance on trajectory predictor design for robotic applications such as collision avoidance and navigation systems.

Results

TaskDatasetMetricValueModel
Trajectory PredictionJAADCF_MSE(1.5)4565BiTrap-D
Trajectory PredictionJAADC_MSE(1.5)1105BiTrap-D
Trajectory PredictionJAADMSE(0.5)93BiTrap-D
Trajectory PredictionJAADMSE(1.0)378BiTrap-D
Trajectory PredictionJAADMSE(1.5)1206BiTrap-D
Trajectory PredictionPIECF_MSE(1.5)1949Bitrap-D
Trajectory PredictionPIEC_MSE(1.5)481Bitrap-D
Trajectory PredictionPIEMSE(0.5)41Bitrap-D
Trajectory PredictionPIEMSE(1.0)161Bitrap-D
Trajectory PredictionPIEMSE(1.5)511Bitrap-D

Related Papers

Multi-Strategy Improved Snake Optimizer Accelerated CNN-LSTM-Attention-Adaboost for Trajectory Prediction2025-07-21GEMINUS: Dual-aware Global and Scene-Adaptive Mixture-of-Experts for End-to-End Autonomous Driving2025-07-19AGENTS-LLM: Augmentative GENeration of Challenging Traffic Scenarios with an Agentic LLM Framework2025-07-18World Model-Based End-to-End Scene Generation for Accident Anticipation in Autonomous Driving2025-07-17Orbis: Overcoming Challenges of Long-Horizon Prediction in Driving World Models2025-07-17Channel-wise Motion Features for Efficient Motion Segmentation2025-07-17LaViPlan : Language-Guided Visual Path Planning with RLVR2025-07-17Safeguarding Federated Learning-based Road Condition Classification2025-07-16