Research map / Multi-agent systems and games / Human-AI and goal-conditioned
RLSLM: A Hybrid Framework Combining Reinforcement Learning and a Rule-based Social Locomotion Model for Socially-aware Navigation
Yitian Kou, Yihe Gu, Chen Zhou, Dandan Zhu, Shu-Guang Kuai
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 heading-relevant social component (HRSC) to the social influence field (ablation) | RLSLM · 42 single-human scenarios | cases passing in front of human: 23 -> 5 | Improved |
| add heading-irrelevant component (HISC) to the social influence field (ablation) | RLSLM · 21 single-human scenarios | Maximum Lateral Distance | Improved |
| add collision avoidance component (CAC) to the social influence field (ablation) | RLSLM · 21 single-human scenarios | Maximum Lateral Distance | Improved |
| increase social weight sigma from 0 to higher values (0.5, 1.0, 2.0) (ablation) | RLSLM · single-human scenarios | Maximum Lateral Distance | Mixed |
| use RLSLM instead of COMPANION and n-Body rule-based navigation | navigation agent · VR comfort rating | comfort rating: Δrating = 1.12 | Improved |
Closest papers by meaning
- Following the Human Thread in Social Navigation (ICLR 2025 · similarity 0.88)
- Uni-RLHF: Universal Platform and Benchmark Suite for Reinforcement Learning with Diverse Human Feedback (ICLR 2024 · similarity 0.86)
- DUO: Diverse, Uncertain, On-Policy Query Generation and Selection for Reinforcement Learning from Human Feedback (AAAI 2025 · similarity 0.86)
- LocoVR: Multiuser Indoor Locomotion Dataset in Virtual Reality (ICLR 2025 · similarity 0.85)
- SENSEI: Semantic Exploration Guided by Foundation Models to Learn Versatile World Models (ICML 2025 · similarity 0.85)
- Personalizing Reinforcement Learning from Human Feedback with Variational Preference Learning (NeurIPS 2024 · similarity 0.85)
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.
