Collision-Free Trajectory Planning for a 6-DoF Free-Floating Space Robot via Hierarchical Decoupling Optimization

Wang, Shengjie; Cao, Yuxue; Zheng, Xiang; Zhang, Tao

doi:10.1109/lra.2022.3152698

Cited by 21 publications

(8 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…However, in our experiments, the method can not work well in a 12-DoF dual-arm environment. The subsequent work mainly focus on the position and attitude decoupling control for the setting of a single robotic arm [26]. Recently, there are some preliminary applications for free-float dual-arm space manipulator.…”

Section: Related Workmentioning

confidence: 99%

A Learning System for Motion Planning of Free-Float Dual-Arm Space Manipulator towards Non-Cooperative Object

Wang¹,

Cao²,

Zheng³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Recent years have seen the emergence of non-cooperative objects in space, like failed satellites and space junk. These objects are usually operated or collected by free-float dual-arm space manipulators. Thanks to eliminating the difficulties of modeling and manual parameter-tuning, reinforcement learning (RL) methods have shown a more promising sign in the trajectory planning of space manipulators. Although previous studies demonstrate their effectiveness, they cannot be applied in tracking dynamic targets with unknown rotation (non-cooperative objects). In this paper, we proposed a learning system for motion planning of free-float dual-arm space manipulator (FFDASM) towards non-cooperative objects. Specifically, our method consists of two modules. Module I realizes the multi-target trajectory planning for two end-effectors within a large target space. Next, Module II takes as input the point clouds of the non-cooperative object to estimate the motional property, and then can predict the position of target points on an non-cooperative object. We leveraged the combination of Module I and Module II to track target points on a spinning object with unknown regularity successfully. Furthermore, the experiments also demonstrate the scalability and generalization of our learning system.

show abstract

Section: Related Workmentioning

confidence: 99%

A Learning System for Motion Planning of Free-Float Dual-Arm Space Manipulator towards Non-Cooperative Object

Wang¹,

Cao²,

Zheng³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Vecerik et al [32] proposed a general and model-free DDPG-based approach for solving high-dimensional robotics problems. Other studies [33,34] have proposed DDPG-based path-planning methods in which HER is used to overcome the performance degradation caused by sparse rewards. TD3 with traditional global path planning was employed in [35] to improve the generalization of the developed model.…”

Section: Introductionmentioning

confidence: 99%

End-to-End Autonomous Navigation Based on Deep Reinforcement Learning with a Survival Penalty Function

Jeng,

Chiang

2023

Sensors

View full text Add to dashboard Cite

An end-to-end approach to autonomous navigation that is based on deep reinforcement learning (DRL) with a survival penalty function is proposed in this paper. Two actor–critic (AC) frameworks, namely, deep deterministic policy gradient (DDPG) and twin-delayed DDPG (TD3), are employed to enable a nonholonomic wheeled mobile robot (WMR) to perform navigation in dynamic environments containing obstacles and for which no maps are available. A comprehensive reward based on the survival penalty function is introduced; this approach effectively solves the sparse reward problem and enables the WMR to move toward its target. Consecutive episodes are connected to increase the cumulative penalty for scenarios involving obstacles; this method prevents training failure and enables the WMR to plan a collision-free path. Simulations are conducted for four scenarios—movement in an obstacle-free space, in a parking lot, at an intersection without and with a central obstacle, and in a multiple obstacle space—to demonstrate the efficiency and operational safety of our method. For the same navigation environment, compared with the DDPG algorithm, the TD3 algorithm exhibits faster numerical convergence and higher stability in the training phase, as well as a higher task execution success rate in the evaluation phase.

show abstract

“…Además, en la actualidad existen varias herramientas y librerías de código abierto para resolver diferentes problemas en el espacio. Por ejemplo, en (Wang et al, 2022) se presenta un algoritmo de optimización de desacoplamiento jerárquico libre de modelos para realizar la planificación de trayectorias multiobjetivo en 6D para el robot espacial de flotación libre.…”

Section: Introductionunclassified

Simulación y control de robots en aplicaciones de servicio en órbita mediante OnOrbitROS

Ramón,

Pomares,

Felicetti

2023

XLIV Jornadas De Automática: Libro De Actas: Universidad De Zaragoza, Escuela De Ingeniería Y Arquitectura, 6, 7 Y 8 De Septiem

View full text Add to dashboard Cite

Actualmente, la utilización de herramientas de simulación como ROS/Gazebo es una práctica habitual para la simulación y desarrollo de algoritmos de control para sistemas robóticos terrestres típicos. Sin embargo, en la actualidad aún no está comúnmente aceptado en la comunidad espacial. Numerosos estudios en el campo de la robótica espacial utilizan herramientas construidas ad-hoc, pero que no están estandarizadas, que no son de código abierto y que, además, no han sido verificadas, lo que complica el desarrollo y la simulación de sistemas robóticos versátiles y algoritmos para el control de sistemas robóticos espaciales. Este artículo propone una solución de código abierto para la simulación de robots espaciales en órbita denominada OnOrbitROS. Este trabajo presenta una descripción de la arquitectura, los diferentes módulos software y las posibilidades de simulación de OnOrbitROS. Se describen las características clave de la herramienta desarrollada, con especial atención a la personalización de las simulaciones y a las posibilidades de ampliación de la herramienta. Con el fin de mostrar estas capacidades, se describen los resultados obtenidos al aplicar OnOrbitROS para la simulación del robot ETS-VII.

show abstract

Collision-Free Trajectory Planning for a 6-DoF Free-Floating Space Robot via Hierarchical Decoupling Optimization

Cited by 21 publications

References 20 publications

A Learning System for Motion Planning of Free-Float Dual-Arm Space Manipulator towards Non-Cooperative Object

A Learning System for Motion Planning of Free-Float Dual-Arm Space Manipulator towards Non-Cooperative Object

End-to-End Autonomous Navigation Based on Deep Reinforcement Learning with a Survival Penalty Function

Simulación y control de robots en aplicaciones de servicio en órbita mediante OnOrbitROS

Contact Info

Product

Resources

About