# Whole-Body Dynamic Throwing with Legged Manipulators

arXiv: https://arxiv.org/abs/2410.05681 · HTML: https://mlsanity.com/paper/2410.05681/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Oct 2024.

## Built on by (most cited first, 2 of 2)

- [Scalable Multi-Objective Robot Reinforcement Learning through Gradient Conflict Resolution](https://mlsanity.com/paper/2509.14816/) (2025)
- [RAPT: Model-Predictive Out-of-Distribution Detection and Failure Diagnosis for Sim-to-Real Humanoid Deployment](https://mlsanity.com/paper/2602.01515/) (2026)

## Abstract (arXiv)

Throwing with a legged robot involves precise coordination of object manipulation and locomotion - crucial for advanced real-world interactions. Most research focuses on either manipulation or locomotion, with minimal exploration of tasks requiring both. This work investigates leveraging all available motors (full-body) over arm-only throwing in legged manipulators. We frame the task as a deep reinforcement learning (RL) objective, optimising throwing accuracy towards any user-commanded target destination and the robot's stability. Evaluations on a humanoid and an armed quadruped in simulation show that full-body throwing improves range, accuracy, and stability by exploiting body momentum, counter-balancing, and full-body dynamics. We introduce an optimised adaptive curriculum to balance throwing accuracy and stability, along with a tailored RL environment setup for efficient learning in sparse-reward conditions. Unlike prior work, our approach generalises to targets in 3D space. We transfer our learned controllers from simulation to a real humanoid platform.