S&AS:INT:Learning and Planning for Dynamic Locomotion

S

• 批准号: 1849343
• 负责人: Alan Fern
• 金额: $ 82万
• 依托单位: Oregon State University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2019
• 资助国家: 美国
• 起止时间: 2019-02-01 至 2025-01-31
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1849343&HistoricalAwards=false
• 关键词: S& INT; Learning; Planning; Dynamic

Despite years of work on robot locomotion, we still do not have robots that can reliably and flexibly move around in homes, workspaces, and natural terrain. For many of these environments, legged robots, as opposed to wheel-based robots, appear to be the most viable option for achieving the desired level of locomotion autonomy. Prior work has produced ATRIAS, a two-legged robot, which was designed to replicate the dynamic properties of human and animal legs, and Cassie, which retains this dynamics-first approach but improves upon ATRIAS by adding steering capability and ankles, along with engineering improvements. Compared to conventional robot-leg designs, the designs of ATRIAS and Cassie carefully incorporate "passive dynamics" into the mechanism, essentially bringing the dynamic behavior of the hardware into partnership with the software control system. This approach has the potential to exhibit locomotion capabilities much closer to humans. However, the flexibility and "springiness" of these human-like legs creates new challenges for locomotion control. While ATRIAS and Cassie are currently able to walk and run outdoors over moderate terrain using basic balance control methods, the methods are still not able to support more complex locomotion activities, such as navigating stairs or rocky terrain. The proposed research will develop new control methods for dynamic legged locomotion, which will enable robots such as ATRIAS and Cassie to effectively move around in our homes, workplaces, and other complex natural environments with much more flexibility, while using much less energy. This will significantly expand on the application domains for which autonomous robot locomotion can be applied. The primary technical contribution of the project will be twofold: First, the research will study machine learning techniques to dramatically improve the existing hand-crafted controllers for dynamic locomotion, and create a rich action space composed of behavior policies that produce robust walking, standing, running, and leaping behaviors with various speeds, step/jump heights, and other characteristics. This action space provides an expressive and compact means of controlling the motion of a legged robot, greatly surpassing direct torque control in expressiveness while also dramatically reducing the dimensionality of the problem. Second, the research will design a fast and efficient sampling-based planning architecture, which also uses machine learning to speed up the planning process to allow for real-time fulfillment of movement goals while avoiding collisions and falls. This work adds new knowledge in research on legged locomotion planning by considering obstacle planning and robot dynamics as an integrated problem. Most prior work attempts to decouple the two pieces, for example by using a planner to find footholds in kinematic space and handing them to a dynamics controller that tries to maintain balance as the robot follows the kinematic goals. For human-like performance in two-legged locomotion, the project considers foothold choice to be intrinsically linked to robot dynamics, and considers foot placement in an integrated way.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

尽管在机器人运动方面进行了多年的研究，但我们仍然没有能够在家庭、工作场所和自然地形中可靠、灵活地移动的机器人。对于许多这样的环境，与轮式机器人相比，腿式机器人似乎是实现所需的自主运动水平的最可行的选择。之前的工作已经产生了 ATRIAS，一种双足机器人，旨在复制人类和动物腿部的动态特性，以及 Cassie，它保留了这种动力学优先的方法，但通过增加转向能力和脚踝以及工程设计对 ATRIAS 进行了改进改进。与传统的机器人腿设计相比，ATRIAS 和 Cassie 的设计仔细地将“被动动力学”融入到机构中，本质上将硬件的动态行为与软件控制系统结合起来。这种方法有可能展现出更接近人类的运动能力。然而，这些类人腿的灵活性和“弹性”给运动控制带来了新的挑战。虽然 ATRIAS 和 Cassie 目前能够使用基本的平衡控制方法在中等地形的户外行走和跑步，但这些方法仍然无法支持更复杂的运动活动，例如在楼梯或岩石地形中导航。拟议的研究将开发用于动态腿部运动的新控制方法，这将使 ATRIAS 和 Cassie 等机器人能够在我们的家庭、工作场所和其他复杂的自然环境中有效地移动，更加灵活，同时使用更少的能源。这将显着扩展自主机器人运动的应用领域。该项目的主要技术贡献将有两个：首先，该研究将研究机器学习技术，以显着改进现有的手工制作的动态运动控制器，并创建一个由行为策略组成的丰富的动作空间，这些行为策略可以产生稳健的行走、站立、具有不同速度、步/跳跃高度和其他特征的跑步和跳跃行为。该动作空间提供了一种富有表现力且紧凑的方式来控制有腿机器人的运动，在表现力上大大超越了直接扭矩控制，同时也大大降低了问题的维度。其次，该研究将设计一种快速高效的基于采样的规划架构，该架构还使用机器学习来加速规划过程，以便实时实现运动目标，同时避免碰撞和跌倒。这项工作通过将障碍物规划和机器人动力学视为一个综合问题，为腿式运动规划的研究增加了新的知识。大多数先前的工作试图将这两部分解耦，例如，通过使用规划器在运动学空间中找到立足点，并将它们交给动态控制器，该控制器试图在机器人遵循运动学目标时保持平衡。对于两足运动中的类人表现，该项目认为立足点选择与机器人动力学有内在联系，并以综合方式考虑足部放置。该奖项反映了 NSF 的法定使命，并通过使用基金会的智力价值和更广泛的影响审查标准。

项目成果

Learning Memory-Based Control for Human-Scale Bipedal Locomotion

学习基于记忆的人体规模双足运动控制

• DOI: 10.15607/rss.2020.xvi.031
• 发表时间: 2020-06-03
• 期刊: ArXiv
• 作者: J. Siekmann;S. Valluri;Jeremy Dao;Lorenzo Bermillo;Helei Duan;Alan Fern;J. Hurst
• 通讯作者: J. Hurst

Learning Dynamic Bipedal Walking Across Stepping Stones

学习动态双足行走踏脚石

• DOI: 10.1109/iros47612.2022.9981884
• 发表时间: 2022-05-03
• 期刊: 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
• 作者: Helei Duan;A. Malik;M. S. Gadde;Jeremy Dao;Alan Fern;J. Hurst
• 通讯作者: J. Hurst

Optimizing Bipedal Locomotion for The 100m Dash With Comparison to Human Running

与人类跑步相比，优化 100m 短跑的双足运动

• DOI: 10.1109/icra48891.2023.10160436
• 发表时间: 2023-05
• 期刊: IEEE
• 作者: Crowley, Devin;Dao, Jeremy;Duan, Helei;Green, Kevin;Hurst, Jonathan;Fern, Alan
• 通讯作者: Fern, Alan

The Choice Function Framework for Online Policy Improvement

在线政策改进的选择函数框架

• DOI: 10.1609/aaai.v34i06.6578
• 发表时间: 2020-06
• 期刊: Proceedings of the AAAI Conference on Artificial Intelligence
• 作者: Issakkimuthu, Murugeswari;Fern, Alan;Tadepalli, Prasad
• 通讯作者: Tadepalli, Prasad

Planning for the Unexpected: Explicitly Optimizing Motions for Ground Uncertainty in Running

为意外情况做好规划：针对跑步中的地面不确定性明确优化运动

• 发表时间: 2020-01
• 期刊: IEEE International Conference on Robotics and Automation
• 作者: Green, Kevin;Hatton, Ross;Hurst, Jonathan
• 通讯作者: Hurst, Jonathan