# Physics-Informed Eikonal Caging for Whole-Arm Manipulation Planning

arXiv: https://arxiv.org/abs/2606.22143 · HTML: https://mlsanity.com/paper/2606.22143/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 59 references that are in the map.
- First posted on arXiv 20 Jun 2026.

## Builds on (most cited first, 27 of 27)

- [Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World](https://mlsanity.com/paper/1703.06907/) (2017)
- [The CMA Evolution Strategy: A Tutorial](https://mlsanity.com/paper/1604.00772/) (2016)
- [Using Simulation and Domain Adaptation to Improve Efficiency of Deep Robotic Grasping](https://mlsanity.com/paper/1709.07857/) (2017)
- [Meta Reinforcement Learning for Sim-to-real Domain Adaptation](https://mlsanity.com/paper/1909.12906/) (2019)
- [Global Planning for Contact-Rich Manipulation via Local Smoothing of Quasi-dynamic Contact Models](https://mlsanity.com/paper/2206.10787/) (2022)
- [Rethinking Robustness Assessment: Adversarial Attacks on Learning-based Quadrupedal Locomotion Controllers](https://mlsanity.com/paper/2405.12424/) (2024)
- [Non-prehensile Planar Manipulation via Trajectory Optimization with Complementarity Constraints](https://mlsanity.com/paper/2109.13145/) (2021)
- [Representing Robot Geometry as Distance Fields: Applications to Whole-body Manipulation](https://mlsanity.com/paper/2307.00533/) (2023)
- [Configuration Space Distance Fields for Manipulation Planning](https://mlsanity.com/paper/2406.01137/) (2024)
- [Robust Reinforcement Learning via Genetic Curriculum](https://mlsanity.com/paper/2202.08393/) (2022)
- [VP-STO: Via-point-based Stochastic Trajectory Optimization for Reactive Robot Behavior](https://mlsanity.com/paper/2210.04067/) (2022)
- [Dexterous Contact-Rich Manipulation via the Contact Trust Region](https://mlsanity.com/paper/2505.02291/) (2025)
- [Cost-to-Go Function Generating Networks for High Dimensional Motion Planning](https://mlsanity.com/paper/2012.06023/) (2020)
- [Complementarity-Free Multi-Contact Modeling and Optimization for Dexterous Manipulation](https://mlsanity.com/paper/2408.07855/) (2024)
- [Certified Grasping](https://mlsanity.com/paper/1909.03985/) (2019)
- [Plan-Guided Reinforcement Learning for Whole-Body Manipulation](https://mlsanity.com/paper/2310.12263/) (2023)
- [Characterizing Manipulation Robustness through Energy Margin and Caging Analysis](https://mlsanity.com/paper/2404.12115/) (2024)
- [Caging in Time: A Framework for Robust Object Manipulation under Uncertainties and Limited Robot Perception](https://mlsanity.com/paper/2410.16481/) (2024)
- [A Riemannian Take on Distance Fields and Geodesic Flows in Robotics](https://mlsanity.com/paper/2412.05197/) (2024)
- [Robust Contact-rich Manipulation through Implicit Motor Adaptation](https://mlsanity.com/paper/2412.11829/) (2024)
- [Causal Domain Restriction for Eikonal Equations](https://mlsanity.com/paper/1309.2884/) (2013)
- [Robust Pushing: Exploiting Quasi-static Belief Dynamics and Contact-informed Optimization](https://mlsanity.com/paper/2404.02795/) (2024)
- [Adversarial Game-Theoretic Algorithm for Dexterous Grasp Synthesis](https://mlsanity.com/paper/2511.05809/) (2025)
- [Free Space of Rigid Objects: Caging, Path Non-Existence, and Narrow Passage Detection](https://mlsanity.com/paper/2002.02715/) (2020)
- [Quasi-static Soft Fixture Analysis of Rigid and Deformable Objects](https://mlsanity.com/paper/2309.01224/) (2023)
- [Robustness-Aware Tool Selection and Manipulation Planning with Learned Energy-Informed Guidance](https://mlsanity.com/paper/2506.03362/) (2025)
- [Scaling Whole-body Multi-contact Manipulation with Contact Optimization](https://mlsanity.com/paper/2508.12980/) (2025)

## Built on by (most cited first, 1 of 1)

- [Energy-Structured Latent World Models with Neural Time Fields for Physically Constistent Open-World Motion Planning](https://mlsanity.com/paper/2608.09876/) (2026)

## Abstract (arXiv)

Planning contact-rich whole-arm manipulation is challenging because interactions that involve extended robot geometry give rise to complex contact dynamics that are difficult to model accurately. This creates a need for planning principles that do not rely heavily on precise contact models. Caging offers one such geometric notion of robustness to modeling inaccuracy by restricting object escape through geometrically enclosing the object. However, existing caging formulations are difficult to incorporate into continuous optimization-based manipulation planning. We reformulate caging as a minimum-time escape problem in which the object seeks to leave an enclosing robot geometry in the shortest time. This yields a continuous escape-time field that measures the robot's enclosure quality and we show it satisfies an eikonal equation. We therefore can approximate this field using a physics-informed neural network, producing a smooth differentiable representation that can be embedded directly into manipulation planning. The resulting objective supports whole-arm manipulation planning to favor robot configurations resisting object escape. This improves the manipulation robustness to contact model mismatch, thus enabling planning with simplified contact models, including quasi-dynamic approximations and simplified object geometry. Across simulation and real-world experiments, we show improved robustness to disturbances and contact-model mismatch relative to baselines. These results suggest that geometric enclosure can serve as a practical robustness primitive for whole-arm manipulation. A supplementary video, which includes an intuitive overview of our method and experiment video results, is available on our project webpage.