# Learning a Unified Control Policy for Safe Falling

## TL;DR

This paper introduces a neural network-based policy for humanoid robots to fall safely by optimizing contact points and timing, achieving high rewards with significantly faster online execution compared to traditional methods.

## Contribution

It presents a novel mixture of actor-critic neural network architecture that jointly solves discrete contact planning and continuous control for safe falling.

## Key findings

- Achieves comparable or higher rewards than dynamic programming search.
- Offers 50 to 400 times faster online execution.
- Successfully determines optimal contact points and timing during falls.

## Abstract

Being able to fall safely is a necessary motor skill for humanoids performing highly dynamic tasks, such as running and jumping. We propose a new method to learn a policy that minimizes the maximal impulse during the fall. The optimization solves for both a discrete contact planning problem and a continuous optimal control problem. Once trained, the policy can compute the optimal next contacting body part (e.g. left foot, right foot, or hands), contact location and timing, and the required joint actuation. We represent the policy as a mixture of actor-critic neural network, which consists of n control policies and the corresponding value functions. Each pair of actor-critic is associated with one of the n possible contacting body parts. During execution, the policy corresponding to the highest value function will be executed while the associated body part will be the next contact with the ground. With this mixture of actor-critic architecture, the discrete contact sequence planning is solved through the selection of the best critics while the continuous control problem is solved by the optimization of actors. We show that our policy can achieve comparable, sometimes even higher, rewards than a recursive search of the action space using dynamic programming, while enjoying 50 to 400 times of speed gain during online execution.