Research map / Multi-agent systems and games / Human-AI and goal-conditioned
TITAN: Future Forecast Using Action Priors
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 action priors to agent interactions and ego-motion priors (ablation) | TITAN future object localization · TITAN test | ADE: 17.79 -> 11.32 | Helped |
| add action priors to agent interactions and ego-motion priors (ablation) | TITAN future object localization · TITAN test | FDE: 27.69 -> 19.53 | Helped |
| add action priors to agent interactions and ego-motion priors (ablation) | TITAN future object localization · TITAN test | FIOU: 0.5650 -> 0.6559 | Helped |
| add action priors to past positions (ablation) | TITAN future object localization · TITAN test | ADE: 38.56 -> 33.54 | Helped |
| add interaction priors without action inputs (ablation) | TITAN future object localization · TITAN test | ADE: 33.54 -> 22.53 | Helped |
| combine ego-motion and interaction priors (ablation) | TITAN future object localization · TITAN test | ADE: 22.53 -> 17.79 | Helped |
| use interaction priors without ego-motion priors (ablation) | TITAN future object localization · TITAN test | ADE: 29.42 -> 22.53 | Helped |
| use action priors without accounting for other agents' motion in the egocentric view (ablation) | TITAN future object localization · TITAN test | ADE: 33.54 -> 29.42 | Hurt |
| add predicted future agent positions without action priors (ablation) | TITAN ego-motion prediction · TITAN test | RMSE (acceleration): 1.201 -> 1.236 | Hurt |
| add action priors to predicted future agent positions (ablation) | TITAN ego-motion prediction · TITAN test | RMSE (acceleration): 1.236 -> 1.182 | Helped |
| use AIM to weight future agent positions without action priors (ablation) | TITAN ego-motion prediction · TITAN test | RMSE (acceleration): 1.182 -> 1.134 | Helped |
| include future position and action in AIM (ablation) | TITAN ego-motion prediction · TITAN test | RMSE (acceleration): 1.134 -> 1.081 | Helped |
Closest papers by meaning
- HalentNet: Multimodal Trajectory Forecasting with Hallucinative Intents (ICLR 2021 · similarity 0.89)
- Motion Forecasting in Continuous Driving (NeurIPS 2024 · similarity 0.87)
- HPNet: Dynamic Trajectory Forecasting with Historical Prediction Attention (CVPR 2024 · similarity 0.87)
- PlaySlot: Learning Inverse Latent Dynamics for Controllable Object-Centric Video Prediction and Planning (ICML 2025 · similarity 0.87)
- Social-Transmotion: Promptable Human Trajectory Prediction (ICLR 2024 · similarity 0.86)
- Future-Aware End-to-End Driving: Bidirectional Modeling of Trajectory Planning and Scene Evolution (NeurIPS 2025 · similarity 0.86)
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.