mlsanityData to 14 Oct 2026

PRISM: Predictive Representation of Interaction Style and Motion for Social Robot Navigation

arXiv 2609.18125 ↗First posted 16 Sep 2026cs.CV cs.ROcited by 0

Not on the map. Why?

Abstract (arXiv)

Humans often observe others before interacting and adjust their behavior accordingly. Robot navigation in crowds, however, often represents pedestrians mainly by observed geometric states, leaving individual differences in interaction tendencies implicit. We propose PRISM (Predictive Representation of Interaction Style and Motion), a framework that infers interaction traits from passive observations of human-human interactions. PRISM encodes human trajectories into a continuous ordinal latent space with a transformer encoder trained by Rank-N-Contrast loss, and pairs each inferred trait with a temporal-stability score supplied to the navigation policy. In randomized crowd simulations, PRISM reduces collision rates over the geometry-only baseline and yields small improvements in navigation-time and path-length metrics. These results suggest the utility of passive latent-trait inference for social navigation in dynamic crowds.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 22 of its 36 references that are in the map. First posted on arXiv 16 Sep 2026.

Builds on

22 of 36 references.

References · 22

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networkscited by 690
  3. 2017DESIRE: Distant Future Prediction in Dynamic Scenes with Interacting Agentscited by 310
  4. 2020It Is Not the Journey but the Destination: Endpoint Conditioned Trajectory Predictioncited by 236
  5. 2019Social-BiGAT: Multimodal Trajectory Forecasting using Bicycle-GAN and Graph Attention Networkscited by 229
  6. 2018Crowd-Robot Interaction: Crowd-aware Robot Navigation with Attention-based Deep Reinforcement Learningcited by 175
  7. 2017Socially Aware Motion Planning with Deep Reinforcement Learningcited by 136
  8. 2022Remember Intentions: Retrospective-Memory-based Trajectory Predictioncited by 86
  9. 2022Rank-N-Contrast: Learning Continuous Representations for Regressioncited by 76
  10. 2022Intention Aware Robot Crowd Navigation with Attention-Based Interaction Graphcited by 53
  11. 2021Towards Robust and Adaptive Motion Forecasting: A Causal Representation Perspectivecited by 40
  12. 2023A Survey on Socially Aware Robot Navigation: Taxonomy and Future Challengescited by 39
10 more
  1. 2021Personalized Trajectory Prediction via Distribution Discriminationcited by 30
  2. 2023Fast Inference and Update of Probabilistic Density Estimation on Trajectory Predictioncited by 27
  3. 2021A Survey on Human-aware Robot Navigationcited by 24
  4. 2024T4P: Test-Time Training of Trajectory Prediction via Masked Autoencoder and Actor-specific Token Memorycited by 20
  5. 2022Motion Style Transfer: Modular Low-Rank Adaptation for Deep Motion Forecastingcited by 12
  6. 2025Physical Plausibility-aware Trajectory Prediction via Locomotion Embodimentcited by 10
  7. 2024HEIGHT: Heterogeneous Interaction Graph Transformer for Robot Navigation in Crowded and Constrained Environmentscited by 9
  8. 2025CacheFlow: Fast Human Motion Prediction by Cached Normalizing Flowcited by 4
  9. 2022Safe and Efficient Exploration of Human Models During Human-Robot Interactioncited by 3
  10. 2026SAMIDARE: Advanced Tracking-by-Segmentation for Dense Scenarioscited by 1

Built on by

Not cited yet.