Research map / Multi-agent systems and games / Human-AI and goal-conditioned
Plan Recognition in Continuous Domains
Read the paperCheck 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 |
|---|---|---|---|
| use RRT* instead of RRTConnect as the recognition planner (ablation) | Mirroring · OMPL cubicles navigation, 10 goals (220 problems) | convergence (%): 8.21 -> 22.52 | Helped |
| use TRRT instead of RRTConnect as recognition planner (ablation) | Mirroring · OMPL cubicles navigation, 10 goals (220 problems) | convergence (%): 8.21 -> 25.82 | Helped |
| use TRRT instead of RRT* as recognition planner (ablation) | Mirroring · OMPL cubicles navigation, 10 goals (220 problems) | time (% of allotted): 100.40 -> 28.10 | Helped |
| use TRRT instead of RRT* as recognition planner (ablation) | Mirroring · OMPL cubicles navigation, 10 goals (220 problems) | convergence (%): 22.52 -> 25.82 | Helped |
| add 9 clustered goals (19 goals instead of 10) | Mirroring with TRRT · OMPL cubicles | convergence (%): 25.82 -> 16.11 | Hurt |
| use continuous planner instead of discretized grid recognition (ablation) | Mirroring · ROS soccer-field | convergence ratio: 0.00 -> 0.46 | Helped |
| use continuous angles instead of 40 degree discretization (ablation) | Mirroring · Octagon shapes | average convergence: 0.13 -> 0.67 | Helped |
| use continuous angles instead of 1 degree discretization (ablation) | Mirroring · Octagon shapes | average convergence: 0.67 -> 0.67 | No clear effect |
| use continuous angles instead of 1 degree discretization (ablation) | Mirroring · Triangle shapes | average convergence: 0.33 -> 0.44 | Helped |
| replace PRP formulation of Ramirez and Geffner with Mirroring | goal recognition · six classical planning domains (450 problems) | ranking of true goal | No clear effect |
Closest papers by meaning
- Learning Planning Domains from Non-redundant Fully-Observed Traces: Theoretical Foundations and Complexity Analysis (AAAI 2024 · similarity 0.89)
- Learning Planning Abstractions from Language (ICLR 2024 · similarity 0.86)
- UniDomain: Pretraining a Unified PDDL Domain from Real-World Demonstrations for Generalizable Robot Task Planning (NeurIPS 2025 · similarity 0.86)
- Differentiable Learning of Lifted Action Schemas for Classical Planning (NeurIPS 2026 · similarity 0.85)
- PlanLLM: Video Procedure Planning with Refinable Large Language Models (AAAI 2025 · similarity 0.85)
- Symbolic Numeric Planning with Patterns (AAAI 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.