RMPs for Safe Impedance Control in Contact-Rich Manipulation

Shaw, Seiji; Abbatematteo, Ben; Konidaris, George

doi:10.1109/icra46639.2022.9811986

Cited by 7 publications

(3 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There has been a set of alternative works, dealing with different problems in Riemannian motion policies. In (Shaw et al, 2021) pullback bundle dynamical systems are proposed. The work proposes a method to combine multiple policies defined in non-Euclidean spaces.…”

Section: Related Workmentioning

confidence: 99%

“…Artificial potential fields (APF) methods (Ge and Cui, 2002; Khatib, 1985) and more recently Riemannian motion policies (RMP) methods (Aljalbout et al, 2021; Bylard et al, 2021; Cheng et al, 2018; Kappler et al, 2018; Ratliff et al, 2018; Shaw et al, 2021) are one of the most popular approaches for reactive motion generation in manipulators. In contrast with path planning or trajectory optimization methods, these methods propose to solve a myopic (one-step ahead) control problem.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Composable energy policies for reactive motion generation and reinforcement learning

Urain

Liu

et al. 2023

The International Journal of Robotics Research

View full text Add to dashboard Cite

In this work, we introduce composable energy policies (CEP), a novel framework for multi-objective motion generation. We frame the problem of composing multiple policy components from a probabilistic view. We consider a set of stochastic policies represented in arbitrary task spaces, where each policy represents a distribution of the actions to solve a particular task. Then, we aim to find the action in the configuration space that optimally satisfies all the policy components. The presented framework allows the fusion of motion generators from different sources: optimal control, data-driven policies, motion planning, and handcrafted policies. Classically, the problem of multi-objective motion generation is solved by the composition of a set of deterministic policies, rather than stochastic policies. However, there are common situations where different policy components have conflicting behaviors, leading to oscillations or the robot getting stuck in an undesirable state. While our approach is not directly able to solve the conflicting policies problem, we claim that modeling each policy as a stochastic policy allows more expressive representations for each component in contrast with the classical reactive motion generation approaches. In some tasks, such as reaching a target in a cluttered environment, we show experimentally that CEP additional expressivity allows us to model policies that reduce these conflicting behaviors. A field that benefits from these reactive motion generators is the one of robot reinforcement learning. Integrating these policy architectures with reinforcement learning allows us to include a set of inductive biases in the learning problem. These inductive biases guide the reinforcement learning agent towards informative regions or improve collision safety while exploring. In our work, we show how to integrate our proposed reactive motion generator as a structured policy for reinforcement learning. Combining the reinforcement learning agent exploration with the prior-based CEP, we can improve the learning performance and explore safer.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Composable energy policies for reactive motion generation and reinforcement learning

Urain

Liu

et al. 2023

The International Journal of Robotics Research

View full text Add to dashboard Cite

show abstract

“…This reactivity makes RMPs well suited for handling disturbances and adapting to changing conditions. However, the application of RMPs has primarily been limited to fully actuated systems [8], such as robotic arms [9]. In a fully actuated system, the number of actuators (motors or joints) is equal to the number of degrees of freedom, allowing the robot to independently control each degree of freedom.…”

Section: Introduction 1backgroundmentioning

confidence: 99%

Learning Advanced Locomotion for Quadrupedal Robots: A Distributed Multi-Agent Reinforcement Learning Framework with Riemannian Motion Policies

Wang,

Sagawa,

Yoshiyasu

2024

Robotics

View full text Add to dashboard Cite

Recent advancements in quadrupedal robotics have explored the motor potential of these machines beyond simple walking, enabling highly dynamic skills such as jumping, backflips, and even bipedal locomotion. While reinforcement learning has demonstrated excellent performance in this domain, it often relies on complex reward function tuning and prolonged training times, and the interpretability is not satisfactory. Riemannian motion policies, a reactive control method, excel in handling highly dynamic systems but are generally limited to fully actuated systems, making their application to underactuated quadrupedal robots challenging. To address these limitations, we propose a novel framework that treats each leg of a quadrupedal robot as an intelligent agent and employs multi-agent reinforcement learning to coordinate the motion of all four legs. This decomposition satisfies the conditions for utilizing Riemannian motion policies and eliminates the need for complex reward functions, simplifying the learning process for high-level motion modalities. Our simulation experiments demonstrate that the proposed method enables quadrupedal robots to learn stable locomotion using three, two, or even a single leg, offering advantages in training speed, success rate, and stability compared to traditional approaches, and better interpretability. This research explores the possibility of developing more efficient and adaptable control policies for quadrupedal robots.

show abstract

Design and Implementation of Dynamic Motion Policy for Multi-Sensor Omnidirectional Mobile Arm Robot System in Human-Robot Coexisted Healthcare Workplace

Wu,

2023

2023 International Conference on Advanced Robotics and Intelligent Systems (ARIS)

View full text Add to dashboard Cite

RMPs for Safe Impedance Control in Contact-Rich Manipulation

Cited by 7 publications

References 16 publications

Composable energy policies for reactive motion generation and reinforcement learning

Composable energy policies for reactive motion generation and reinforcement learning

Learning Advanced Locomotion for Quadrupedal Robots: A Distributed Multi-Agent Reinforcement Learning Framework with Riemannian Motion Policies

Design and Implementation of Dynamic Motion Policy for Multi-Sensor Omnidirectional Mobile Arm Robot System in Human-Robot Coexisted Healthcare Workplace

Contact Info

Product

Resources

About