Research map / Multi-agent systems and games / Human-AI and goal-conditioned
Trajectron++: Dynamically-Feasible Trajectory Forecasting With Heterogeneous Data
Tim Salzmann, Boris Ivanovic, Punarjay Chakravarty, Marco Pavone
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add dynamics integration (ablation) | Trajectron++ · nuScenes vehicles KDE NLL @1s | KDE NLL: 0.81 -> -4.28 | Improved |
| add dynamics integration (ablation) | Trajectron++ · nuScenes vehicles FDE @1s | FDE (m): 0.18 -> 0.07 | Improved |
| add dynamics integration (ablation) | Trajectron++ · nuScenes vehicles road boundary violations @4s | boundary violation (%): 6.9 -> 8.1 | Hurt |
| add dynamics integration (ablation) | Trajectron++ (Full) · ETH/UCY KDE NLL average | KDE NLL: -0.74 -> -1.14 | Improved |
| add map encoding to dynamics integration (ablation) | Trajectron++ · nuScenes vehicles road boundary violations @4s | boundary violation (%): 8.1 -> 7.6 | Improved |
| add map encoding to dynamics integration (ablation) | Trajectron++ · nuScenes vehicles FDE @4s | FDE (m): 2.17 -> 2.20 | No clear effect |
| add map encoding (ablation) | Trajectron++ · ETH Univ obstacle violations (all pedestrians) | collision rate (%): 4.6% -> 1.0% | Improved |
| add map encoding (ablation) | Trajectron++ · ETH Univ obstacle violations (pedestrians near obstacles) | collision rate (%): 21.5% -> 4.9% | Improved |
| add ego-robot future motion plan encoding (ablation) | Trajectron++ · nuScenes vehicles FDE @4s (excl. ego) | FDE (m): 2.09 -> 1.50 | Improved |
| add ego-robot future motion plan encoding (ablation) | Trajectron++ · nuScenes vehicles road boundary violations @4s (excl. ego) | boundary violation (%): 7.6 -> 4.2 | Improved |
| replace undirected graph and CVAE of Trajectron with Trajectron++ Full | Trajectron · ETH/UCY average best of 20 | ADE (m): 0.47 -> 0.19 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- SoPhie — SoPhie: An Attentive GAN for Predicting Paths Compliant to Social and Physical Constraints (CVPR 2019) · better on 2 of 2 shared results
- CAR-Net — CAR-Net: Clairvoyant Attentive Recurrent Network (ECCV 2018) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- DeMo: Decoupling Motion Forecasting into Directional Intentions and Dynamic States (NeurIPS 2024 · similarity 0.89)
- AutoTraces: Autoregressive Trajectory Forecasting via Multimodal Large Language Models (CVPR 2026 · similarity 0.89)
- SmartRefine: A Scenario-Adaptive Refinement Framework for Efficient Motion Prediction (CVPR 2024 · similarity 0.88)
- HPNet: Dynamic Trajectory Forecasting with Historical Prediction Attention (CVPR 2024 · similarity 0.88)
- TrajAgent: An LLM-Agent Framework for Trajectory Modeling via Large-and-Small Model Collaboration (NeurIPS 2025 · similarity 0.88)
- Trajeglish: Traffic Modeling as Next-Token Prediction (ICLR 2024 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
