Learning Agile Humanoid Dodgeball with Onboard Monocular Vision
Organizations: ETH Zurich, Switzerland. · RWTH Aachen University, Germany. · Robotic Systems Lab, ETH Zurich, Switzerland.
Abstract
Humanoid robots operating in shared, dynamic environments must respond to rapidly approaching objects while maintaining balance. We study dodgeball as a controlled test of this capability, coupling visual threat assessment with whole-body evasion, recovery, and target reacquisition. We develop a system that integrates onboard monocular perception, temporal ball-state and threat-flag estimation, and learned whole-body control. A ball detector supplies bounding-box histories, and a temporal estimator predicts relative ball position and a binary threat flag. Separate dodge/recovery and search/track policies share this interface and are composed to support repeated encounters. A three-stage curriculum first trains control with privileged ball states, then starts estimator supervision from stable policy rollouts, and finally replaces the actor's privileged inputs with estimator outputs. Analytic projection and perception randomization provide detector-like training observations without image rendering. Across approach-angle bins in controlled simulation, dodge success ranges from 97.8--100.0% for 5.0 m launches at 6 m/s to 33.2--40.8% for 2.5 m launches at 10 m/s, with 1000 throws per speed--distance condition. On a physical Unitree G1, controlled single-throw success exceeds 85% over more than 15 trials. A hardware sequence demonstrates full-azimuth target reacquisition followed by another dodge. These results demonstrate an integrated onboard-monocular-vision system under highly dynamic motions.
Figures & tables
| Component | Objective and intended behavior |
|---|---|
| Dodge | Avoid ball contact and increase minimum body-to-ball clearance. |
| Recovery | Reduce planar motion, yaw rate, and deviation from the ready pose after evasion. |
| Search/track | Align horizontal facing direction with the ball to acquire and maintain visibility. |
| Regularization | Discourage unstable or unnecessarily aggressive whole-body motion. |
| Noise | Dodge (%) | Error (m) | Threat acc. (%) | Non-threat rec. (%) | Threat rec. (%) |
|---|---|---|---|---|---|
| Clean | 83.53 | 0.1854 | 95.37 | 99.41 | 87.84 |
| Small | 84.40 | 0.2130 | 94.55 | 98.30 | 87.50 |
| Medium | 73.00 | 0.2496 | 91.75 | 94.10 | 87.42 |
| Large | 26.90 | 0.3424 | 87.55 | 89.24 | 84.47 |
| Training variant | Dodge (%) | Error (m) |
|---|---|---|
| Full Stages | 90.8 | 0.2614 |
| Direct Training | 74.1 | 0.2742 |
| No Bootstrap | 80.6 | 0.2152 |
| No Estimator Warmup | 67.6 | 0.5572 |
| Domain | Task | Result |
|---|---|---|
| Simulation | Consecutive dodge | 10/10 |
| Simulation | Full-azimuth search | 10/10 |
| Hardware | Single throws | , |
| Hardware | Reacquisition + dodge | Suppl. Video |
Humanoid Robot Control
Humanoid robot control develops methods for coordinating bipedal balance, locomotion, and whole-body interaction with people and objects.
See all 222 papers