# PAC-MAN: Perception-Aware CBF-RL for Whole-Body Safety in Humanoid Dodgeball

arXiv: https://arxiv.org/abs/2607.28623 · HTML: https://mlsanity.com/paper/2607.28623/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 36 references that are in the map.
- First posted on arXiv 30 Jul 2026.

## Builds on (most cited first, 29 of 29)

- [Control Barrier Function Based Quadratic Programs for Safety Critical Systems](https://mlsanity.com/paper/1609.06408/) (2016)
- [BeyondMimic: From Motion Tracking to Versatile Humanoid Control via Guided Diffusion](https://mlsanity.com/paper/2508.08241/) (2025)
- [Extreme Parkour with Legged Robots](https://mlsanity.com/paper/2309.14341/) (2023)
- [ANYmal Parkour: Learning Agile Navigation for Quadrupedal Robots](https://mlsanity.com/paper/2306.14874/) (2023)
- [Reinforcement Learning for Robust Parameterized Locomotion Control of Bipedal Robots](https://mlsanity.com/paper/2103.14295/) (2021)
- [SONIC: Supersizing Motion Tracking for Natural Humanoid Whole-Body Control](https://mlsanity.com/paper/2511.07820/) (2025)
- [Humanoid Parkour Learning](https://mlsanity.com/paper/2406.10759/) (2024)
- [GMT: General Motion Tracking for Humanoid Whole-Body Control](https://mlsanity.com/paper/2506.14770/) (2025)
- [Retargeting Matters: General Motion Retargeting for Humanoid Motion Tracking](https://mlsanity.com/paper/2510.02252/) (2025)
- [Agile But Safe: Learning Collision-Free High-Speed Legged Locomotion](https://mlsanity.com/paper/2401.17583/) (2024)
- [OmniRetarget: Interaction-Preserving Data Generation for Humanoid Whole-Body Loco-Manipulation and Scene Interaction](https://mlsanity.com/paper/2509.26633/) (2025)
- [Humanoid Locomotion and Manipulation: Current Progress and Challenges in Control, Planning, and Learning](https://mlsanity.com/paper/2501.02116/) (2025)
- [AMO: Adaptive Motion Optimization for Hyper-Dexterous Humanoid Whole-Body Control](https://mlsanity.com/paper/2505.03738/) (2025)
- [RSL-RL: A Learning Library for Robotics Research](https://mlsanity.com/paper/2509.10771/) (2025)
- [Opt2Skill: Imitating Dynamically-feasible Whole-Body Trajectories for Versatile Humanoid Loco-Manipulation](https://mlsanity.com/paper/2409.20514/) (2024)
- [Sim-to-Real Learning for Humanoid Box Loco-Manipulation](https://mlsanity.com/paper/2310.03191/) (2023)
- [HITTER: A HumanoId Table TEnnis Robot via Hierarchical Planning and Learning](https://mlsanity.com/paper/2508.21043/) (2025)
- [VisualMimic: Visual Humanoid Loco-Manipulation via Motion Tracking and Generation](https://mlsanity.com/paper/2509.20322/) (2025)
- [mjlab: A Lightweight Framework for GPU-Accelerated Robot Learning](https://mlsanity.com/paper/2601.22074/) (2026)
- [Perceptive Humanoid Parkour: Chaining Dynamic Human Skills via Motion Matching](https://mlsanity.com/paper/2602.15827/) (2026)
- [A Collision-Free MPC for Whole-Body Dynamic Locomotion and Manipulation](https://mlsanity.com/paper/2202.12385/) (2022)
- [CBF-RL: Safety Filtering Reinforcement Learning in Training with Control Barrier Functions](https://mlsanity.com/paper/2510.14959/) (2025)
- [SMP: Reusable Score-Matching Motion Priors for Physics-Based Character Control](https://mlsanity.com/paper/2512.03028/) (2025)
- [Walk the PLANC: Physics-Guided RL for Agile Humanoid Locomotion on Constrained Footholds](https://mlsanity.com/paper/2601.06286/) (2026)
- [Deep Whole-body Parkour](https://mlsanity.com/paper/2601.07701/) (2026)
- [CReF: Cross-modal and Recurrent Fusion for Depth-conditioned Humanoid Locomotion](https://mlsanity.com/paper/2603.29452/) (2026)
- [BAT: Balancing Agility and Stability via Online Policy Switching for Long-Horizon Whole-Body Humanoid Control](https://mlsanity.com/paper/2604.01064/) (2026)
- [Egocentric Tactile and Proximity Sensors as Observation Priors for Humanoid Collision Avoidance](https://mlsanity.com/paper/2604.25554/) (2026)
- [TAGA: Terrain-aware Active Gaze Learning for Generalizable Agile Humanoid Locomotion](https://mlsanity.com/paper/2606.05880/) (2026)

## Built on by (most cited first, 3 of 3)

- [DODGER: Safety-Guided Reinforcement Learning for Robot Navigation Among Dynamic Obstacles](https://mlsanity.com/paper/2609.38873/) (2026)
- [FAITH: Feasibility-Aware Safety-Filtered RL for High-Dimensional Systems](https://mlsanity.com/paper/2610.12432/) (2026)
- [CSF: Contextual Safety Filtering for Motion Generators](https://mlsanity.com/paper/2610.12467/) (2026)

## Abstract (arXiv)

We present PAC-MAN, a perception-aware CBF-RL framework that couples control-barrier safety with deployment-realistic onboard sensing for whole-body humanoid dodgeball. The deployed policy sees the ball only as segmentation-masked depth from a head-mounted camera, while training-time CBF guidance represents clearance to every body link, and an adversarial motion prior regularizes the resulting evasive reflexes. We evaluate on a controlled any-link contact benchmark with seeded throws in two regimes: single throws and a deployment loop in which the robot walks back to its station and recovers between throws. On this benchmark, the policy comes within a few points of a privileged state oracle: a fixed onboard camera alone is adequate for evasion. We find that usable barrier structure depends on perceptual observability: Joint-CBF gives the best performance with accurate ball states, degrades under fixed-camera observations when used only as training guidance, and recovers with a ball-tracking gimbal or privileged runtime filter. We therefore deploy a lightweight Link-CBF policy zero-shot on the Unitree G1 in the real world, where it tolerates imperfect perception, succeeds on 95% of throws, and uses semantic segmentation to dodge different balls.