Research map / Vision-language and multimodal / Robot action and navigation
AGiLe: Learning Robust Long-Horizon Manipulation via Affordance-Grounded Bidirectional Latent Planning
Zixuan Chen, Xiangrong Feng, Jieqi Shi, Lin Shao, Jing Huo, Yang Gao
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 forward critic loss to the backward planner training (ablation) | AGiLe · LIBERO-LONG | average success rate (%): 89.0 -> 97.1 | Improved |
| add forward critic loss to the backward planner training (ablation) | AGiLe · LIBERO-LONG | perfectly solved tasks: 3 / 10 -> 7 / 10 | Improved |
| add affordance grounding via cross-attention (ablation) | AGiLe · LIBERO-LONG | average success rate (%): 90.5 -> 97.1 | Improved |
| add affordance grounding via cross-attention (ablation) | AGiLe · LIBERO-LONG | perfectly solved tasks: 2 / 10 -> 7 / 10 | Improved |
| AGiLe bidirectional planning with affordance versus backward-only LBP | latent backward planning · LIBERO-LONG | average success rate (%): 88.6 -> 97.1 | Improved |
| AGiLe versus LBP on late stages of real-world 6-stage tasks | latent backward planning · real-world long-horizon tasks | stage-wise score: LBP falls to 5% (Task 3) and 2% (Task 4) in later stages | Improved |
| AGiLe versus LBP on 'Put both pots on stove' | latent backward planning · LIBERO-LONG task 9 | success rate (%): 60.0 -> 78.6 | Improved |
| AGiLe versus Seer on perfect-task count | forward-predictive planners · LIBERO-LONG | tasks with 100% success: Seer 1, LBP 3, AGiLe 7 of 10 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- Seer — SEER: Backdoor Detection for Vision-Language Models through Searching Target Text and Image Trigger Jointly (AAAI 2024) · 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
- Instruction-Augmented Long-Horizon Planning: Embedding Grounding Mechanisms in Embodied Mobile Manipulation (AAAI 2025 · similarity 0.90)
- AffordDP: Generalizable Diffusion Policy with Transferable Affordance (CVPR 2025 · similarity 0.90)
- FLIP: Flow-Centric Generative Planning as General-Purpose Manipulation World Model (ICLR 2025 · similarity 0.88)
- RoboCerebra: A Large-scale Benchmark for Long-horizon Robotic Manipulation Evaluation (NeurIPS 2025 · similarity 0.88)
- Affordances-Oriented Planning Using Foundation Models for Continuous Vision-Language Navigation (AAAI 2025 · similarity 0.88)
- Zero-Shot Robotic Manipulation with Pre-Trained Image-Editing Diffusion Models (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.
