Research map / Probabilistic and scientific modeling / Dynamical systems
Improving Robotic Tactile Localization Super-resolution via Spatiotemporal Continuity Learning and Overlapping Air Chambers
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 causal convolution to model pressure time series rather than a static MLP (ablation) | Tactile localization · Single-point pressing | MAEx (mm): 0.230 -> 0.147 | Helped |
| Increase causal-convolution time-window length from T=2 to T=9 (ablation) | Tactile localization · Single-point pressing | MAEx (mm): 0.194 -> 0.147 | Helped |
| Increase causal-convolution time-window length beyond T=9 (ablation) | Tactile localization · Single-point pressing | MAEx (mm): 0.147 -> 0.151 | No clear effect |
| Use denser training-data sampling (ablation) | Causal convolution tactile localization · Tactile localization dataset | MAEx (mm): 0.306 -> 0.147 | Helped |
| Train on data matching the test indenter diameter (ablation) | Tactile localization · Indenter D=2, D=6, and D=10 | MAE (mm): 0.174 vs 0.361; 0.154 vs 0.333; 0.169 vs 0.308 | Helped |
| Train on a mixed dataset of indenter diameters (ablation) | Tactile localization · Test D=2, D=6, and D=10 | MAE (mm): 0.268; 0.221; 0.308 | Mixed |
Closest papers by meaning
- Sensor-Invariant Tactile Representation (ICLR 2025 · similarity 0.87)
- AnyTouch: Learning Unified Static-Dynamic Representation across Multiple Visuo-tactile Sensors (ICLR 2025 · similarity 0.86)
- Tactile MNIST: Benchmarking Active Tactile Perception (NeurIPS 2026 · similarity 0.86)
- Touch in the Wild: Learning Fine-Grained Manipulation with a Portable Visuo-Tactile Gripper (NeurIPS 2025 · similarity 0.85)
- EgoTac: In-the-wild Tactile Prediction from Egocentric Vision (NeurIPS 2026 · similarity 0.85)
- DIFFTACTILE: A Physics-based Differentiable Tactile Simulator for Contact-rich Robotic Manipulation (ICLR 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.