# Egocentric Tactile and Proximity Sensors as Observation Priors for Humanoid Collision Avoidance

arXiv: https://arxiv.org/abs/2604.25554 · HTML: https://mlsanity.com/paper/2604.25554/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 18 references that are in the map.
- First posted on arXiv 28 Apr 2026.

## Builds on (most cited first, 14 of 14)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Object Detection in 20 Years: A Survey](https://mlsanity.com/paper/1905.05055/) (2019)
- [Asymmetric Actor Critic for Image-Based Robot Learning](https://mlsanity.com/paper/1710.06542/) (2017)
- [Contact Anticipation for Physical Human-Robot Interaction with Robotic Manipulators using Onboard Proximity Sensors](https://mlsanity.com/paper/2110.11516/) (2021)
- [Enhancing Tactile-based Reinforcement Learning for Robotic Control](https://mlsanity.com/paper/2510.21609/) (2025)
- [Collision-Free Humanoid Traversal in Cluttered Indoor Scenes](https://mlsanity.com/paper/2601.16035/) (2026)
- [Learning Soccer Skills for Humanoid Robots: A Progressive Perception-Action Framework](https://mlsanity.com/paper/2602.05310/) (2026)
- [AuraSense: Robot Collision Avoidance by Full Surface Proximity Detection](https://mlsanity.com/paper/2108.04867/) (2021)
- [Proximity Perception in Human-Centered Robotics: A Survey on Sensing Systems and Applications](https://mlsanity.com/paper/2108.07206/) (2021)
- [ARMOR: Egocentric Perception for Humanoid Robot Collision Avoidance and Motion Planning](https://mlsanity.com/paper/2412.00396/) (2024)
- [GenTact Toolbox: A Computational Design Pipeline to Procedurally Generate Context-Driven 3D Printed Whole-Body Artificial Skins](https://mlsanity.com/paper/2412.00711/) (2024)
- [Generating Whole-Body Avoidance Motion through Localized Proximity Sensing](https://mlsanity.com/paper/2412.04649/) (2024)
- [Whole-body Multi-contact Motion Control for Humanoid Robots Based on Distributed Tactile Sensors](https://mlsanity.com/paper/2505.19580/) (2025)
- [Design, Mapping, and Contact Anticipation with 3D-printed Whole-Body Tactile and Proximity Sensors](https://mlsanity.com/paper/2603.04714/) (2026)

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

- [PAC-MAN: Perception-Aware CBF-RL for Whole-Body Safety in Humanoid Dodgeball](https://mlsanity.com/paper/2607.28623/) (2026)

## Abstract (arXiv)

Collision-free motion is often aided by tactile and proximity sensors distributed on the body of the robot due to their resistance to occlusion as opposed to external cameras. However, how to shape the sensor's properties, such as sensing coverage; type; and range, to enable avoidant behavior remains unclear. In this work, we present a reinforcement learning framework for whole-body collision avoidance on a humanoid H1-2 robot and use it to characterize how sensor properties shape learned avoidance behavior. Using dodgeball as a benchmark task, we ablate the properties of sensors distributed across the upper body of the robot and find that raw proximity measurements can substitute for explicit object localization provided the sensing range is sufficient and that sparse non-directional proximity signals outpace dense directional alternatives in sample efficiency.