The Stanford LittleDog: A learning and rapid replanning approach to quadruped locomotion

2011 ◽  
Vol 30 (2) ◽  
pp. 150-174 ◽  
Author(s):  
J. Zico Kolter ◽  
Andrew Y Ng
Keyword(s):  
Software Architecture ◽  
Learning Algorithms ◽  
Quadruped Robot ◽  
Legged Robots ◽  
Rapid Recovery ◽  
Quadruped Locomotion ◽  
Planning And Control ◽  
Run Time ◽  
And Control ◽  
Wheeled Vehicles

Legged robots have the potential to navigate a wide variety of terrain that is inaccessible to wheeled vehicles. In this paper we consider the planning and control tasks of navigating a quadruped robot over challenging terrain, including terrain that it has not seen until run-time. We present a software architecture that makes use of both static and dynamic gaits, as well as specialized dynamic maneuvers, to accomplish this task. Throughout the paper we highlight two themes that have been central to our approach: (1) the prevalent use of learning algorithms, and (2) a focus on rapid recovery and replanning techniques; we present several novel methods and algorithms that we developed for the quadruped and that illustrate these two themes. We evaluate the performance of these different methods, and also present and discuss the performance of our system on the official Learning Locomotion tests.

Learning, planning, and control for quadruped locomotion over challenging terrain

2010 ◽  
Vol 30 (2) ◽  
pp. 236-258 ◽  
Author(s):  
Mrinal Kalakrishnan ◽  
Jonas Buchli ◽  
Peter Pastor ◽  
Michael Mistry ◽  
Stefan Schaal
Keyword(s):  
Inverse Dynamics ◽  
Leg Length ◽  
Quadruped Locomotion ◽  
Planning And Control ◽  
Floating Base ◽  
Planning Optimization ◽  
Optimization And Control ◽  
Zero Moment ◽  
External Test ◽  
And Control

We present a control architecture for fast quadruped locomotion over rough terrain. We approach the problem by decomposing it into many sub-systems, in which we apply state-of-the-art learning, planning, optimization, and control techniques to achieve robust, fast locomotion. Unique features of our control strategy include: (1) a system that learns optimal foothold choices from expert demonstration using terrain templates , (2) a body trajectory optimizer based on the Zero-Moment Point (ZMP) stability criterion, and (3) a floating-base inverse dynamics controller that, in conjunction with force control, allows for robust, compliant locomotion over unperceived obstacles. We evaluate the performance of our controller by testing it on the LittleDog quadruped robot, over a wide variety of rough terrains of varying difficulty levels. The terrain that the robot was tested on includes rocks, logs, steps, barriers, and gaps, with obstacle sizes up to the leg length of the robot. We demonstrate the generalization ability of this controller by presenting results from testing performed by an independent external test team on terrain that has never been shown to us.

Java Simulator for Quadruped Walking Robot

2010 ◽  
Vol 166-167 ◽  
pp. 445-450
Author(s):  
Steliana Vatau ◽  
Valentin Ciupe ◽  
Inocentiu Maniu
Keyword(s):  
Legged Robots ◽  
High Dimensional ◽  
Legged Robot ◽  
Walking Robot ◽  
Quadruped Locomotion ◽  
Java Language ◽  
Cross Platform ◽  
Simulation And Control ◽  
Physics Based Simulation ◽  
And Control

With advances in science and technology, the interest to study the animals walking has developed the demand for building the legged robots. Physics-based simulation and control of quadruped locomotion is difficult because quadrupeds are unstable, under actuated, high-dimensional dynamical systems. We develop a simple control strategy that can be used to generate a large variety of gaits and styles in real-time, including walking in all directions (forwards, backwards, sideways, turning). The application named JQuadRobot is developed in Java and Java3D API. A Graphical User Interface and a simulator for a custom quadruped leg's robot and the main features of the interface are presented in this paper. This application is developed in Java and is essential in a development motion for legged robot. The friendly interface, allows any user to define and test movements for this robot. The cross-platform capability was the first reason to choose Java language for developing this application.

Towards More Possibilities: Motion Planning and Control for Hybrid Locomotion of Wheeled-Legged Robots

2020 ◽  
Vol 5 (2) ◽  
pp. 3723-3730
Author(s):  
Jingyuan Sun ◽  
Yangwei You ◽  
Xuran Zhao ◽  
Albertus Hendrawan Adiwahono ◽  
Chee Meng Chew
Keyword(s):  
Motion Planning ◽  
Legged Robots ◽  
Planning And Control ◽  
Hybrid Locomotion ◽  
And Control

scholarly journals Evaluation of Reinforcement and Deep Learning Algorithms in Controlling Unmanned Aerial Vehicles

2021 ◽  
Vol 11 (16) ◽  
pp. 7240
Author(s):  
Yalew Zelalem Jembre ◽  
Yuniarto Wimbo Nugroho ◽  
Muhammad Toaha Raza Khan ◽  
Muhammad Attique ◽  
Rajib Paul ◽  
...  
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Unmanned Aerial Vehicles ◽  
Physical Environment ◽  
Learning Algorithms ◽  
Q Learning ◽  
Planning And Control ◽  
Aerial Vehicles ◽  
Reinforcement Learning Models ◽  
And Control

Unmanned Aerial Vehicles (UAVs) are abundantly becoming a part of society, which is a trend that is expected to grow even further. The quadrotor is one of the drone technologies that is applicable in many sectors and in both military and civilian activities, with some applications requiring autonomous flight. However, stability, path planning, and control remain significant challenges in autonomous quadrotor flights. Traditional control algorithms, such as proportional-integral-derivative (PID), have deficiencies, especially in tuning. Recently, machine learning has received great attention in flying UAVs to desired positions autonomously. In this work, we configure the quadrotor to fly autonomously by using agents (the machine learning schemes being used to fly the quadrotor autonomously) to learn about the virtual physical environment. The quadrotor will fly from an initial to a desired position. When the agent brings the quadrotor closer to the desired position, it is rewarded; otherwise, it is punished. Two reinforcement learning models, Q-learning and SARSA, and a deep learning deep Q-network network are used as agents. The simulation is conducted by integrating the robot operating system (ROS) and Gazebo, which allowed for the implementation of the learning algorithms and the physical environment, respectively. The result has shown that the Deep Q-network network with Adadelta optimizer is the best setting to fly the quadrotor from the initial to desired position.

Sign in / Sign up

Export Citation Format

Share Document