TrafficBots V1.5: Traffic Simulation via Conditional VAEs and Transformers with Relative Pose Encoding
Not on the map. Why?
Abstract (arXiv)
In this technical report we present TrafficBots V1.5, a baseline method for the closed-loop simulation of traffic agents. TrafficBots V1.5 achieves baseline-level performance and a 3rd place ranking in the Waymo Open Sim Agents Challenge (WOSAC) 2024. It is a simple baseline that combines TrafficBots, a CVAE-based multi-agent policy conditioned on each agent's individual destination and personality, and HPTR, the heterogeneous polyline transformer with relative pose encoding. To improve the performance on the WOSAC leaderboard, we apply scheduled teacher-forcing at the training time and we filter the sampled scenarios at the inference time. The code is available at https://github.com/zhejz/TrafficBotsV1.5.
Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). Builds on 18 of its 23 references that are in the map. First posted on arXiv 16 Jun 2024.
Builds on
18 of 23 references.
References · 18
- 2017Attention Is All You Needcited by 59,932
- 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
- 2018Learning Latent Dynamics for Planning from Pixelscited by 1,221
- 2015Scheduled Sampling for Sequence Prediction with Recurrent Neural Networkscited by 779
- 2020VectorNet: Encoding HD Maps and Agent Dynamics from Vectorized Representationcited by 528
- 2022Wayformer: Motion Forecasting via Simple & Efficient Attention Networkscited by 279
- 2021TrafficSim: Learning to Simulate Realistic Multi-Agent Behaviorscited by 192
- 2021End-to-End Urban Driving by Imitating a Reinforcement Learning Coachcited by 191
- 2022Imitation Is Not Enough: Robustifying Imitation with Reinforcement Learning for Challenging Driving Scenarioscited by 124
- 2020Implicit Latent Variable Model for Scene-Consistent Motion Forecastingcited by 116
- 2023The Waymo Open Sim Agents Challengecited by 86
- 2022GoRela: Go Relative for Viewpoint-Invariant Motion Forecastingcited by 68
6 more
- 2023TrafficBots: Towards World Models for Autonomous Driving Simulation and Motion Predictioncited by 56
- 2024BehaviorGPT: Smart Agent Simulation for Autonomous Driving with Next-Patch Predictioncited by 49
- 2023Real-Time Motion Prediction via Heterogeneous Polyline Transformer with Relative Pose Encodingcited by 32
- 2023Multiverse Transformer: 1st Place Solution for Waymo Open Sim Agents Challenge 2023cited by 25
- 2024SMART: Scalable Multi-agent Real-time Motion Generation via Next-token Predictioncited by 25
- 2023Learning Realistic Traffic Agents in Closed-loopcited by 24
Built on by
Citing papers per year: 2024: 2; 2025: 8; 2026: 3.
13 papers.
Sort:
By area:
- 2024Closed-Loop Supervised Fine-Tuning of Tokenized Traffic Modelscited by 40
- 2024KiGRAS: Kinematic-Driven Generative Model for Realistic Agent Simulationcited by 17
- 2025DRoPE: Directional Rotary Position Embedding for Efficient Agent Interaction Modelingcited by 9
- 2025Highly Accurate and Diverse Traffic Data: The DeepScenario Open 3D Datasetcited by 7
- 2025Generative AI for Autonomous Driving: Frontiers and Opportunitiescited by 7
- 2025When Planners Meet Reality: How Learned, Reactive Traffic Agents Shift nuPlan Benchmarkscited by 7
- 2025Autoregressive Meta-Actions for Unified Controllable Trajectory Generationcited by 2
- 2025Long-term Traffic Simulation with Interleaved Autoregressive Motion and Scenario Generationcited by 2
- 2025SceneStreamer: Continuous Scenario Generation as Next Token Group Predictioncited by 2
- 2026SCORP: Scene-Consistent Multi-agent Diffusion Planning with Stable Online Reinforcement Post-Training for Cooperative Drivingcited by 2
- 2026RLFTSim: Realistic and Controllable Multi-Agent Traffic Simulation via Reinforcement Learning Fine-Tuningcited by 2
- 2025Unlocking Efficient Vehicle Dynamics Modeling via Analytic World Modelscited by 1
- 2026RLFTSim: Realistic and Controllable Multi-Agent Traffic Simulation via Reinforcement Learning Fine-Tuning18 May 2026
- 2026Artificial Intelligence for Modeling and Simulation of Mixed Automated and Human Traffic14 Apr 2026
- 2026SCORP: Scene-Consistent Multi-agent Diffusion Planning with Stable Online Reinforcement Post-Training for Cooperative Driving13 Apr 2026
- 2025When Planners Meet Reality: How Learned, Reactive Traffic Agents Shift nuPlan Benchmarks16 Oct 2025
- 2025SceneStreamer: Continuous Scenario Generation as Next Token Group Prediction29 Jun 2025
- 2025Long-term Traffic Simulation with Interleaved Autoregressive Motion and Scenario Generation20 Jun 2025
- 2025Autoregressive Meta-Actions for Unified Controllable Trajectory Generation29 May 2025
- 2025Generative AI for Autonomous Driving: Frontiers and Opportunities13 May 2025
- 2025Highly Accurate and Diverse Traffic Data: The DeepScenario Open 3D Dataset24 Apr 2025
- 2025DRoPE: Directional Rotary Position Embedding for Efficient Agent Interaction Modeling19 Mar 2025
- 2025Unlocking Efficient Vehicle Dynamics Modeling via Analytic World Models14 Feb 2025
- 2024Closed-Loop Supervised Fine-Tuning of Tokenized Traffic Models5 Dec 2024
1 more
- 2024Closed-Loop Supervised Fine-Tuning of Tokenized Traffic Modelscited by 40
- 2024KiGRAS: Kinematic-Driven Generative Model for Realistic Agent Simulationcited by 17
- 2025DRoPE: Directional Rotary Position Embedding for Efficient Agent Interaction Modelingcited by 9
- 2025Highly Accurate and Diverse Traffic Data: The DeepScenario Open 3D Datasetcited by 7
- 2025When Planners Meet Reality: How Learned, Reactive Traffic Agents Shift nuPlan Benchmarkscited by 7
- 2025Autoregressive Meta-Actions for Unified Controllable Trajectory Generationcited by 2
- 2025Long-term Traffic Simulation with Interleaved Autoregressive Motion and Scenario Generationcited by 2
- 2025SceneStreamer: Continuous Scenario Generation as Next Token Group Predictioncited by 2
- 2026RLFTSim: Realistic and Controllable Multi-Agent Traffic Simulation via Reinforcement Learning Fine-Tuningcited by 2
- 2026Artificial Intelligence for Modeling and Simulation of Mixed Automated and Human Trafficcited by 0
- 2026RLFTSim: Realistic and Controllable Multi-Agent Traffic Simulation via Reinforcement Learning Fine-Tuning18 May 2026
- 2026Artificial Intelligence for Modeling and Simulation of Mixed Automated and Human Traffic14 Apr 2026
- 2025When Planners Meet Reality: How Learned, Reactive Traffic Agents Shift nuPlan Benchmarks16 Oct 2025
- 2025SceneStreamer: Continuous Scenario Generation as Next Token Group Prediction29 Jun 2025
- 2025Long-term Traffic Simulation with Interleaved Autoregressive Motion and Scenario Generation20 Jun 2025
- 2025Autoregressive Meta-Actions for Unified Controllable Trajectory Generation29 May 2025
- 2025Highly Accurate and Diverse Traffic Data: The DeepScenario Open 3D Dataset24 Apr 2025
- 2025DRoPE: Directional Rotary Position Embedding for Efficient Agent Interaction Modeling19 Mar 2025
- 2024Closed-Loop Supervised Fine-Tuning of Tokenized Traffic Models5 Dec 2024
- 2024KiGRAS: Kinematic-Driven Generative Model for Realistic Agent Simulation17 Jul 2024