Elsevier

Computer-Aided Design

Volume 59, February 2015, Pages 23-38
Computer-Aided Design

An interactive motion planning framework that can learn from experience

https://doi.org/10.1016/j.cad.2014.07.007Get rights and content

Highlights

  • Maximal sphere sequence represents the scenario. The centerline of maximal sphere sequence represents the scenario skeleton.

  • The motion of object has close relationship with the change of the skeleton and volume size of scenario.

  • Motion learning is based on computing the similarity of scenarios by dynamic time warping (DTW).

  • Scenario retrieval is highly efficient due to the hierarchical clustering in motion library.

  • Releasing humans from rotation manipulation in complex assembly verification with learned motion experience.

Abstract

The accessibility verification of the assembly/disassembly plays an important role in the process of product design. In the last decade, the sampling based motion planners have been successfully applied to solve the accessibility verification. However, the narrow passage which is a common problem in the assembly tasks is still a bottleneck. Meanwhile, the requirement of perception and emotion assessment drives the interaction between users and automatic path planners in the virtual assembly process. In this paper, a curve matching method is used to explore the implicit relationship between the topological information of scenarios and the motion of objects, based on which an interactive motion planning framework that can learn from experience is constructed.

Our framework consists of two main processes: a learning process and a motion generation process. In the former process, the motion segment (a part of motion path) and its related scenario segment (a part of workspace passed through by the object) are gathered, after an interactive motion planning process finds a collision-free motion path or reaches the conclusion of inaccessibility. According to the similarity between the skeletons of scenario segments, the gathered scenario segments and motion segments are organized by a hierarchical structure in the motion library. The latter process permits users to control only one point in the workspace for the selection of a new scenario, and then the similar scenarios are retrieved from the motion library, to help quickly detect the connectivity of the new scenario and generate a repaired motion path to guide users with feasible manipulations. We highlight the performance of our framework on a challenging problem in 2D, in which a non-convex object passes through a cluttered environment filled with randomly shaped and located non-convex obstacles.

Introduction

The verification of accessibility in assembly and disassembly is an essential issue for the product design. However, the accessibility verification presents challenges to both humans and computers. For humans, the manual manipulation of 3D object in a complex virtual environment is extremely difficult  [1]. For computers, the accessibility verification can be defined as computing a collision-free path for an object between a free location and a pre-designed location. In the last decade, the sampling based motion planners have been successfully used to solve the motion planning problems  [2]. However, the performance of sampling based planning algorithms may degrade if the collision-free space contains narrow passages  [3], i.e. small regions whose removal or perturbation can change the connectivity of the collision-free space  [4]. In particular, the narrow passages commonly exist in the virtual assembly/disassembly tasks. Moreover, if no collision-free path exists, the sampling based algorithms may run for a long time before verifying that  [5]. Different heuristics have been created to bias the automatic planners. Decomposition based planners decompose the configuration space into different levels of cells and get an approximate corridor with A algorithm, then explore this corridor to find a collision-free path  [6], [7]. Obstacle based planners either plan motion compliant to the C-contact space (C-contact space is the subset of configuration space, which consists of the configurations when the robot touches one or more obstacles without any penetration  [4]) with geometric formulations  [8], [9], or increase the sampling around the obstacle  [10], [11] and in the C-contact space  [12]. In  [13], the vectors generated on the triangulated meshes of CAD models are used to guide the extension of basic RRT planner (Rapidly-exploring Random Trees). Retraction based planners attempt to improve the sampling in narrow passages through retracting the in-collision configuration to the nearest configuration in the C-contact space  [4], [14]. Despite some improvements, the narrow passage is still a major issue for the sampling based planners. The weak consciousness to the local changes of geometric space results in the above difficulties.

Moreover, designers need to test and verify the geometric constraints to the articulate system of a human skeleton. A direct method is adding a digital human mannequin into the reasoning loop of an automatic method  [1]. The quality of the generated motion of the mannequin becomes a major issue, which mainly concerns reducing the redundant degrees of freedom and making the motion look more natural. Besides, a key challenge for the designers is to analyze end-users’ responses in the design process and to promote product innovation, but users’ preferences cannot be precisely formulated  [15]. Hence, the optimization of the preference of users is today extremely difficult for an automatic method, and the integration with the direct participation of designers is an essential stage  [16], [17].

A solution to the above challenges is to make humans interact with an automatic motion planner. By relaxing the collision constraints, it is easier for a human to find a motion solution. Interactive motion planners attempt to integrate humans with the automatic path planners. The method in  [18] enables users with an haptic device to visually specify some critical via-configurations or sub-goals in the workspace, which guide the exploration of a sampling based planner. However, in the practice, some via-configurations in complex environments are unlikely to be found by humans, or unreachable. In  [6], [19], a preliminary discretization of configuration space is carried out by a decomposition algorithm, and then a corridor between the initial configuration and the goal configuration is found. In this corridor, the harmonic functions are formulated to provide force feedback and a sampling based planner searches a feasible path. Although these kind of methods successfully accelerate the automatic planner by reducing the search space, humans impose very limited impact on the planning process. The method proposed in  [20] is successfully applied to the interactive motion planning of a steerable needle, but not applicable to a non-convex object. In  [21], the method simply allows the simultaneous cooperation between users and automatic algorithms. But humans and automatic planners cooperate in a relatively independent manner. In the “narrow passages”, both of them may fall into a trap and cannot guide each other efficiently.

Learning experience to serve motion planning in new environments has been studied by various works. Recent research focuses on exploiting the accumulated data in the prior planning results. In  [22], the approach proposes to learn from the prior instances of collision queries and to improve the sampling based motion planners in avoidance of the exact collision checking. The “retrieve and repair” idea of  [23] is similar to ours. However, their retrieval process based on the amount of constraints violated by a path is implemented in a robot’s configuration space, which limits their adaptability to quite different environments. In  [24], a more robust and adaptive motion learning method is proposed to map from the previously optimized trajectories in old situations to the good trajectories in new situations. Although similar to our idea of retrieving paths based on the similarity of workspace, their method is limited to an offline constructed motion library composed of optimized motion trajectories. In contrast, the concept of online motion learning based on the topological similarity between scenarios has been proposed in  [25], however, no concrete or workable method was developed by the authors. Given the workspace WS (WSR2 in 2D; WSR3 in 3D) and its subset taken up by the obstacles WSobstacle, the scenario for a moving object is the subset of the workspace excluding the obstacles, which is noted as WSscenario,WSscenario={x|xWS,xWSobstacle}. In this paper, the relationship between the topology of scenarios and the motion of objects is discovered, and based on it a novel scenario retrieval and motion reuse strategy is proposed.

In this paper, a novel framework for the interactive motion learning and generation is proposed. The learning is dynamic: the motion library can constantly evolve from an empty one to a very large one, and it is maintained by a balanced hierarchical structure. More detailed contributions include:

  • The use of the maximal sphere sequence to represent the scenario. The centerline and the radius change of the sphere sequence can respectively describe the topological structure and the volume change of the scenario. The method of the real time generation of the maximal sphere sequence is also provided.

  • A novel motion learning framework based on computing the similarity of the topological structure and the volume change of scenarios.

  • The great acceleration of the motion planning process, especially in narrow passages, thanks to the adequate learning and motion generation strategy.

  • Simplified ways of interacting with a computer by releasing humans from the rotational manipulations, which make it possible to use non-haptic devices in a complex assembly/disassembly task.

We have applied our algorithms and demonstrated its effect in a challenging case in 2D. The rest of the paper is organized in the following manner. Section  2 briefly surveys the related tools in other domains. Section  3 is dedicated to the detailed explanation of our framework. Simulation results are presented and analyzed in the Section  4. The limitations and extensions are discussed in the Section  5.

Section snippets

Related tools from other domains

The recent developments in the fields of motion primitive, medial axis, curve skeleton and curve matching are the basis of our motion learning and generation framework.

Interactive motion learning and generation

In this section, a hypothesis is proposed to describe the relationship between the motion of an object and its corresponding scenario. Then an overview of our motion learning and generation framework is demonstrated prior to the detailed explanations of each functional module.

Implementation and results

In the following section, our motion planning framework will be applied to a non-convex object moving in a cluttered 2D environment which contains the randomly shaped and located non-convex obstacles. The experimental results demonstrate the efficiency of our method. Moreover, after adequate learning, the dependence on the haptic devices can be greatly reduced in the interaction process by releasing users from the rotation manipulations.

All the experimental results are performed on the software

Conclusion and extension

Based on the hypothesis that the motion of an object has a close relationship with the topological structure and the volume size of the scenario, we proposed our interactive motion learning and generation framework, and then applied it to a challenging motion planning problem in 2D. For the first time, the topological similarity between scenarios is used to explore the patterns of motion in configuration space. The experimental results verified our hypothesis. Due to the highly efficient

References (49)

  • Zhang L, Manocha D. An efficient retraction-based RRT planner. In: Proceedings of international conference on robotics...
  • L. Zhang et al.

    Efficient cell labelling and path non-existence computation using C-obstacle query

    Int J Robot Res

    (2008)
  • Ladeveze N, Fourquet JY, Puel B, Taix M. Haptic assembly and disassembly task assistance using interactive path...
  • J. Rosell et al.

    Motion planning for haptic guidance

    J Intell Robot Syst

    (2008)
  • X. Ji et al.

    Planning motions compliant to complex contact states

    Int J Robot Res

    (2001)
  • Peng Tang et al.

    Automatic generation of high-level contact state space between 3D curved objects

    Int J Robot Res

    (2008)
  • Hsin-Yi Y, Thomas S, Eppstein D, Amato NM. UOBPRM: a uniformly distributed obstacle-based PRM. In: Proceedings of...
  • S. Zheng et al.

    Narrow passage sampling for probabilistic roadmap planning

    IEEE Trans Robot

    (2005)
  • Redon S, Lin MC. Practical local planning in the contact space. In: Proceedings of international conference on robotics...
  • Rodriguez S, Xinyu T, Jyh-Ming L, Amato NM. An obstacle-based rapidly-exploring random tree. In: Proceedings of...
  • M. Saha et al.

    Finding narrow passages with probabilistic roadmaps: the small-step retraction method

    Auton Robots

    (2005)
  • E. Poirson et al.

    Eliciting user perceptions using assessment tests based on an interactive genetic algorithm

    J Mech Des

    (2013)
  • Vázquez Hurtado C, Rosell Gratacòs J. Haptic guidance based on harmonic functions for the execution of teleoperated...
  • Patil S, Alterovitz R. Interactive motion planning for steerable needles in 3D environments with obstacles. In: 3rd...
  • Cited by (0)

    View full text