Online, Interactive User Guidance for High-dimensional, Constrained Motion Planning

We consider the problem of planning a collision-free path for a high-dimensional robot. Specifically, we suggest a planning framework where a motion-planning algorithm can obtain guidance from a user. In contrast to existing approaches that try to speed up planning by incorporating experiences or demonstrations ahead of planning, we suggest to seek user guidance only when the planner identifies that it ceases to make significant progress towards the goal. Guidance is provided in the form of an intermediate configuration q^, which is used to bias the planner to go through q^. We demonstrate our approach for the case where the planning algorithm is Multi-Heuristic A* (MHA*) and the robot is a 34-DOF humanoid. We show that our approach allows to compute highly-constrained paths with little domain knowledge. Without our approach, solving such problems requires carefully-crafted domain-dependent heuristics.

Download Full-text

Sampling-Based Motion Planning for Free-Floating Space Robot without Inverse Kinematics

Applied Sciences ◽

10.3390/app10249137 ◽

2020 ◽

Vol 10 (24) ◽

pp. 9137

Author(s):

Hongwen Zhang ◽

Zhanxia Zhu

Keyword(s):

Motion Planning ◽

Inverse Kinematics ◽

Random Trees ◽

Space Robot ◽

Initial Configuration ◽

First Order ◽

System A ◽

Planning Framework ◽

Planning Algorithm ◽

Differential Relationship

Motion planning is one of the most important technologies for free-floating space robots (FFSRs) to increase operation safety and autonomy in orbit. As a nonholonomic system, a first-order differential relationship exists between the joint angle and the base attitude of the space robot, which makes it pretty challenging to implement the relevant motion planning. Meanwhile, the existing planning framework must solve inverse kinematics for goal configuration and has the limitation that the goal configuration and the initial configuration may not be in the same connected domain. Thus, faced with these questions, this paper investigates a novel motion planning algorithm based on rapidly-exploring random trees (RRTs) for an FFSR from an initial configuration to a goal end-effector (EE) pose. In a motion planning algorithm designed to deal with differential constraints and restrict base attitude disturbance, two control-based local planners are proposed, respectively, for random configuration guiding growth and goal EE pose-guiding growth of the tree. The former can ensure the effective exploration of the configuration space, and the latter can reduce the possibility of occurrence of singularity while ensuring the fast convergence of the algorithm and no violation of the attitude constraints. Compared with the existing works, it does not require the inverse kinematics to be solved while the planning task is completed and the attitude constraint is preserved. The simulation results verify the effectiveness of the algorithm.

Download Full-text

A sampling-based optimized algorithm for task-constrained motion planning

International Journal of Advanced Robotic Systems ◽

10.1177/1729881419847378 ◽

2019 ◽

Vol 16 (3) ◽

pp. 172988141984737 ◽

Cited By ~ 1

Author(s):

Kai Mi ◽

Haojian Zhang ◽

Jun Zheng ◽

Jianhua Hu ◽

Dengxiang Zhuang ◽

...

Keyword(s):

Motion Planning ◽

Sampling Methods ◽

Tracking Error ◽

Joint Space ◽

Planning Problem ◽

Redundant Manipulators ◽

Task Space ◽

Constrained Motion ◽

Smooth Path ◽

Planning Algorithm

We consider a motion planning problem with task space constraints in a complex environment for redundant manipulators. For this problem, we propose a motion planning algorithm that combines kinematics control with rapidly exploring random sampling methods. Meanwhile, we introduce an optimization structure similar to dynamic programming into the algorithm. The proposed algorithm can generate an asymptotically optimized smooth path in joint space, which continuously satisfies task space constraints and avoids obstacles. We have confirmed that the proposed algorithm is probabilistically complete and asymptotically optimized. Finally, we conduct multiple experiments with path length and tracking error as optimization targets and the planning results reflect the optimization effect of the algorithm.

Download Full-text

Velocity Obstacle-Based Collision Avoidance and Motion Planning Framework for Connected and Automated Vehicles

Transportation Research Record Journal of the Transportation Research Board ◽

10.1177/03611981211070286 ◽

2022 ◽

pp. 036119812110702

Author(s):

Shunchao Wang ◽

Zhibin Li ◽

Bingtong Wang ◽

Jingfeng Ma ◽

Jingcai Yu

Keyword(s):

Motion Planning ◽

Collision Avoidance ◽

Motion Tracking ◽

Collision Risk ◽

Automated Vehicles ◽

Vehicle Collision ◽

Planning Framework ◽

Planning Algorithm ◽

Velocity Obstacle ◽

Vehicle Dynamic Model

This study proposes a novel collision avoidance and motion planning framework for connected and automated vehicles based on an improved velocity obstacle (VO) method. The controller framework consists of two parts, that is, collision avoidance method and motion planning algorithm. The VO algorithm is introduced to deduce the velocity conditions of a vehicle collision. A collision risk potential field (CRPF) is constructed to modify the collision area calculated by the VO algorithm. A vehicle dynamic model is presented to predict vehicle moving states and trajectories. A model predictive control (MPC)-based motion tracking controller is employed to plan collision-avoidance path according to the collision-free principles deduced by the modified VO method. Five simulation scenarios are designed and conducted to demonstrate the control maneuver of the proposed controller framework. The results show that the constructed CRPF can accurately represent the collision risk distribution of the vehicles with different attributes and motion states. The proposed framework can effectively handle the maneuver of obstacle avoidance, lane change, and emergency response. The controller framework also presents good performance to avoid crashes under different levels of collision risk strength.

Download Full-text

Chance Constrained Motion Planning for High-Dimensional Robots

2019 International Conference on Robotics and Automation (ICRA) ◽

10.1109/icra.2019.8793660 ◽

2019 ◽

Author(s):

Siyu Dai ◽

Shawn Schaffert ◽

Ashkan Jasour ◽

Andreas Hofmann ◽

Brian Williams

Keyword(s):

Motion Planning ◽

High Dimensional ◽

Constrained Motion

Download Full-text

Learning the Metric of Task Constraint Manifolds for Constrained Motion Planning

Electronics ◽

10.3390/electronics7120395 ◽

2018 ◽

Vol 7 (12) ◽

pp. 395 ◽

Cited By ~ 2

Author(s):

Fusheng Zha ◽

Yizhou Liu ◽

Wei Guo ◽

Pengfei Wang ◽

Mantian Li ◽

...

Keyword(s):

Motion Planning ◽

Success Rate ◽

Configuration Space ◽

Fundamental Problem ◽

Approximate Model ◽

High Dimensional ◽

Constrained Motion ◽

Task Constraint ◽

Task Constraints ◽

Planning Methods

Finding feasible motion for robots with high-dimensional configuration space is a fundamental problem in robotics. Sampling-based motion planning algorithms have been shown to be effective for these high-dimensional systems. However, robots are often subject to task constraints (e.g., keeping a glass of water upright, opening doors and coordinating operation with dual manipulators), which introduce significant challenges to sampling-based motion planners. In this work, we introduce a method to establish approximate model for constraint manifolds, and to compute an approximate metric for constraint manifolds. The manifold metric is combined with motion planning methods based on projection operations, which greatly improves the efficiency and success rate of motion planning tasks under constraints. The proposed method Approximate Graph-based Constrained Bi-direction Rapidly Exploring Tree (AG-CBiRRT), which improves upon CBiRRT, and CBiRRT were tested on several task constraints, highlighting the benefits of our approach for constrained motion planning tasks.

Download Full-text

Constrained motion planning for open-chain industrial robots

Robotica ◽

10.1017/s026357471000024x ◽

2010 ◽

Vol 29 (3) ◽

pp. 403-420 ◽

Cited By ~ 5

Author(s):

Gianluca Antonelli ◽

Cataldo Curatella ◽

Alessandro Marino

Keyword(s):

Motion Planning ◽

Industrial Robots ◽

Robot Motion ◽

Constrained Motion ◽

Open Chain ◽

Physical Constraints ◽

Industrial Manipulators ◽

Planning Algorithm ◽

Wide Perspective ◽

Point To Point

SUMMARYIn the industrial environment, several constraints affect the robot motion planning. These are imposed by manufacturing considerations, such as, e.g., to strictly follow a given path, or by physical constraints, such as, e.g., to avoid torque saturation. Among the others, limitation on the velocity, acceleration, and jerk at the joints is often required by the robot manufacturers. In this paper, a motion planning algorithm for open-chain robot manipulators that takes into account several constraints simultaneously is presented. The algorithm developed approaches the motion planning algorithm from a wide perspective, solving systematically the joint as well as the Cartesian motion, both for the point-to-point and the fly movements. The validation has been performed first by numerical simulations and then by experiments on two different industrial manipulators, with different size, with and without the presence of a payload, by imposing demanding trajectories where all the constraints have been excited.

Download Full-text

Generation and Selection of Driver-behavior-based Transferable Motion Primitives

10.21203/rs.3.rs-56830/v1 ◽

2020 ◽

Author(s):

Haijie Guan ◽

Boyang Wang ◽

Jiaming Wei ◽

Yaomin Lu ◽

Huiyan Chen ◽

...

Keyword(s):

Motion Planning ◽

Driver Behavior ◽

Single Step ◽

Driving Experience ◽

Motion Primitives ◽

Planning Framework ◽

Planning Algorithm ◽

Behavior Based ◽

Motion Characteristics ◽

Selection Of

Abstract In order to achieve the integration of driver experience and heterogeneous vehicle platform characteristics in the motion planning algorithm, based on the driver-behavior-based transferable motion primitives, a general motion planning framework for oine generation and online selection of motion primitives (MPs) is proposed. The optimal control theory is applied to solve the boundary value problems in the process of generating MPs, where the driver behaviors and the vehicle motion characteristics are integrated into the optimization in the form of constraints. Moreover, this paper proposes a layered, unequal-weighted MPs selection framework and utilizes the combination of environmental constraints, nonholonomic vehicle constraints, trajectory smoothness, and collision risk as the single-step extension evaluation index. The library of MPs generated oine demonstrates that the proposed generation method realizes the eective expansion of the MP types and achieves the diverse generation of MPs with various velocity attributes and platform types. We also present how the MP selection algorithm utilizes the unique MP library to achieve the online extension of MP sequences. The results show that the proposed motion planning framework can not only improve the eciency and rationality of the algorithm based on driving experience but also can transfer between heterogeneous vehicle platforms and highlight the unique motion characteristics of the platform.

Download Full-text

Generation and Selection of Driver-Behavior-Based Transferable Motion Primitives

10.21203/rs.3.rs-56830/v2 ◽

2021 ◽

Author(s):

Haijie Guan ◽

Boyang Wang ◽

Jiaming Wei ◽

Yaomin Lu ◽

Huiyan Chen ◽

...

Keyword(s):

Motion Planning ◽

Driver Behavior ◽

Single Step ◽

Driving Experience ◽

Motion Primitives ◽

Planning Framework ◽

Planning Algorithm ◽

Behavior Based ◽

Motion Characteristics ◽

Selection Of

Abstract In order to achieve the integration of driver experience and heterogeneous vehicle platform characteristics in the motion planning algorithm, based on the driver-behavior-based transferable motion primitives, a general motion planning framework for offline generation and online selection of motion primitives (MPs) is proposed. The optimal control theory is applied to solve the boundary value problems in the process of generating MPs, where the driver behaviors and the vehicle motion characteristics are integrated into the optimization in the form of constraints. Moreover, this paper proposes a layered, unequal-weighted MPs selection framework and utilizes the combination of environmental constraints, nonholonomic vehicle constraints, trajectory smoothness, and collision risk as the single-step extension evaluation index. The library of MPs generated offline demonstrates that the proposed generation method realizes the effective expansion of the MP types and achieves the diverse generation of MPs with various velocity attributes and platform types. We also present how the MP selection algorithm utilizes the unique MP library to achieve the online extension of MP sequences. The results show that the proposed motion planning framework can not only improve the efficiency and rationality of the algorithm based on driving experience but also can transfer between heterogeneous vehicle platforms and highlight the unique motion characteristics of the platform.

Download Full-text