Learning Stabilizing Control Policies for a Tensegrity Hopper with Augmented Random Search

04/06/2020
by   Vladislav Kurenkov, et al.
0

In this paper, we consider tensegrity hopper - a novel tensegrity-based robot, capable of moving by hopping. The paper focuses on the design of the stabilizing control policies, which are obtained with Augmented Random Search method. In particular, we search for control policies which allow the hopper to maintain vertical stability after performing a single jump. It is demonstrated, that the hopper can maintain a vertical configuration, subject to the different initial conditions and with changing control frequency rates. In particular, lowering control frequency from 1000Hz in training to 500Hz in execution did not affect the success rate of the balancing task.

READ FULL TEXT
research
01/02/2020

From Drinking Philosophers to Wandering Robots

In this paper, we consider the multi-robot path execution problem where ...
research
10/18/2017

Sim-to-Real Transfer of Robotic Control with Dynamics Randomization

Simulations are attractive environments for training agents as they prov...
research
04/05/2022

Configuration Path Control

Reinforcement learning methods often produce brittle policies – policies...
research
05/19/2022

CAMEO: Curiosity Augmented Metropolis for Exploratory Optimal Policies

Reinforcement Learning has drawn huge interest as a tool for solving opt...
research
07/27/2022

PI-ARS: Accelerating Evolution-Learned Visual-Locomotion with Predictive Information Representations

Evolution Strategy (ES) algorithms have shown promising results in train...
research
02/22/2023

Snake and Snake Robot Locomotion in Complex, 3-D Terrain

Snakes can traverse almost all types of environments by bending their el...
research
11/30/2020

Optimal exploitation of renewable resource stocks: Necessary conditions

We study a model for the exploitation of renewable stocks developed in C...

Please sign up or login with your details

Forgot password? Click here to reset