Research map / Multi-agent systems and games / Human-AI and goal-conditioned
RobustNav: Towards Benchmarking Robustness in Embodied Navigation
Prithvijit Chattopadhyay, Judy Hoffman, Roozbeh Mottaghi, Aniruddha Kembhavi
This paper tried a common change: Add data augmentation
add data augmentation (Random-Crop, Random-Shift, Color-Jitter) · PointNav Lower-FOV · SR: 42.49 -> 71.70 Improved
What 689 accepted papers report for this change
- 560 improved
- 44 no clear effect
- 26 mixed
- 59 hurt
- Understanding Multimodal Learning: A Loss Landscape Smoothness Perspective ICML 2026 · add data augmentation (jitter, crop, flip) · UPMC-Food101 · accuracy: 92.84 -> 94.93Improved
- AsyncBEV: Cross-modal flow alignment in Asynchronous 3D Object Detection ICLR 2026 · add EMC + asynchronous data augmentation training · nuScenes val, 0 s offset · NDS: 66.7 -> 63.1Hurt
- Towards Understanding Continual Factual Knowledge Acquisition of Language Models: From Theory to Algorithm ICML 2026 · add data augmentation (5 biographies per individual) in pre-training · Biography PT test, unseen templates · EM: 2.71 -> 81.27Improved
See this change in detailMatched by the wording of each paper's own result, read by AI from the full text. Papers report gains more often than failures, so this shows what gets published, not the chance a change works.
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 Spatter corruption to RGB input | PointNav RGB · PointNav | SR: 98.82 -> 33.58 | Hurt |
| add Motor Failure dynamics corruption | PointNav RGB · PointNav | SR: 98.82 -> 20.56 | Hurt |
| add Low Lighting corruption | PointNav RGB · PointNav | SR: 98.82 -> 94.36 | Hurt |
| add a clean depth sensor (RGB-D instead of RGB) | PointNav · PointNav under Spatter | SR: 33.58 -> 98.91 | Improved |
| add a clean depth sensor (RGB-D instead of RGB) | ObjectNav · ObjectNav under Spatter | SR: 6.76 -> 21.10 | Improved |
| add data augmentation (Random-Crop, Random-Shift, Color-Jitter) | PointNav RGB · PointNav Lower-FOV | SR: 42.49 -> 71.70 | Improved |
| add data augmentation (Random-Crop, Random-Shift, Color-Jitter) | PointNav RGB · PointNav Spatter | SR: 33.58 -> 23.93 | Hurt |
| add action-prediction auxiliary pretraining | PointNav RGB · PointNav Defocus Blur | SR: 75.89 -> 83.35 | Improved |
| add self-supervised adaptation after action-prediction pretraining | PointNav RGB + AP · PointNav Defocus Blur | SR: 83.35 -> 40.95 | Hurt |
| add rotation-prediction pretraining | PointNav RGB · PointNav Defocus Blur | SR: 75.89 -> 32.21 | Hurt |
| add self-supervised adaptation after rotation-prediction pretraining | PointNav RGB + RP · PointNav Spatter | SR: 23.48 -> 61.06 | Improved |
| fine-tune with task supervision on target corruption | PointNav RGB · PointNav Spatter | SR: 33.58 -> 91.81 | Improved |
Closest papers by meaning
- Seeing through Uncertainty: Robust Task-Oriented Optimization in Visual Navigation (NeurIPS 2025 · similarity 0.88)
- C-NAV: Towards Self-Evolving Continual Object Navigation in Open World (NeurIPS 2025 · similarity 0.88)
- Image2Sim: Scaling Embodied Navigation via Generative Neural Simulator (NeurIPS 2026 · similarity 0.88)
- Habitat Synthetic Scenes Dataset (HSSD-200): An Analysis of 3D Scene Scale and Realism Tradeoffs for ObjectGoal Navigation (CVPR 2024 · similarity 0.87)
- HASARD: A Benchmark for Vision-Based Safe Reinforcement Learning in Embodied Agents (ICLR 2025 · similarity 0.87)
- DynaNav: Dynamic Feature and Layer Selection for Efficient Visual Navigation (NeurIPS 2025 · similarity 0.87)
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.
