An RRT-based path planner for use in trajectory imitation

Claassens, Jonathan

doi:10.1109/robot.2010.5509596

Cited by 11 publications

(11 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Prior work has investigated the use of RRTs combined with learned metrics to generate paths, but these methods are guaranteed to converge to a suboptimal solution [15]. One approach extends RRTs to sample only inside a provided number of standard deviations of a mean demonstrated trajectory, but may not find a feasible solution even if one exists [11]. RRTs have also been used in conjunction with task-based symbolic constraints [14].…”

Section: Related Workmentioning

confidence: 99%

Demonstration-Guided Motion Planning

Alterovitz

2016

Springer Tracts in Advanced Robotics

View full text Add to dashboard Cite

We present demonstration-guided motion planning (DGMP), a new framework for planning motions for personal robots to perform household tasks. DGMP combines the strengths of sampling-based motion planning and robot learning from demonstrations to generate plans that (1) avoid novel obstacles in cluttered environments, and (2) learn and maintain critical aspects of the motion required to successfully accomplish a task. Sampling-based motion planning methods are highly effective at computing paths from start to goal configurations that avoid obstacles, but task constraints (e.g. a glass of water must be held upright to avoid a spill) must be explicitly enumerated and programmed. Instead, we use a set of expert demonstrations and automatically extract time-dependent task constraints by learning low variance aspects of the demonstrations, which are correlated with the task constraints. We then introduce multi-component rapidly-exploring roadmaps (MC-RRM), a sampling-based method that incrementally computes a motion plan that avoids obstacles and optimizes a learned cost metric. We demonstrate the effectiveness of DGMP using the Aldebaran Nao robot performing household tasks in a cluttered environment, including moving a spoon full of sugar from a bowl to a cup and cleaning the surface of a table.

show abstract

Section: Related Workmentioning

confidence: 99%

Demonstration-Guided Motion Planning

Alterovitz

2016

Springer Tracts in Advanced Robotics

View full text Add to dashboard Cite

show abstract

“…Recent sampling-based motion planners have also investigated integrating motion constraints and properties learned from demonstrations. Algorithms include sampling only inside a user-specified number of standard deviations of a mean demonstrated trajectory [9], finding low-cost paths over cost maps using local optimization [10], locally optimizing a specified objective function using gradient descent [11], and enforcing constraints using sampling strategies [12]. Prior sampling-based motion planning approaches, unlike our proposed method, do not simultaneously guarantee asymptotic optimality and allow for time-dependent task constraints.…”

Section: Related Workmentioning

confidence: 99%

Asymptotically Optimal Motion Planning for Learned Tasks Using Time-Dependent Cost Maps

Bowen

Alterovitz

2015

IEEE Trans. Automat. Sci. Eng.

View full text Add to dashboard Cite

In unstructured environments in people’s homes and workspaces, robots executing a task may need to avoid obstacles while satisfying task motion constraints, e.g., keeping a plate of food level to avoid spills or properly orienting a finger to push a button. We introduce a sampling-based method for computing motion plans that are collision-free and minimize a cost metric that encodes task motion constraints. Our time-dependent cost metric, learned from a set of demonstrations, encodes features of a task’s motion that are consistent across the demonstrations and, hence, are likely required to successfully execute the task. Our sampling-based motion planner uses the learned cost metric to compute plans that simultaneously avoid obstacles and satisfy task constraints. The motion planner is asymptotically optimal and minimizes the Mahalanobis distance between the planned trajectory and the distribution of demonstrations in a feature space parameterized by the locations of task-relevant objects. The motion planner also leverages the distribution of the demonstrations to significantly reduce plan computation time. We demonstrate the method’s effectiveness and speed using a small humanoid robot performing tasks requiring both obstacle avoidance and satisfaction of learned task constraints. Note to Practitioners Motivated by the desire to enable robots to autonomously operate in cluttered home and workplace environments, this paper presents an approach for intuitively training a robot in a manner that enables it to repeat the task in novel scenarios and in the presence of unforeseen obstacles in the environment. Based on user-provided demonstrations of the task, our method learns features of the task that are consistent across the demonstrations and that we expect should be repeated by the robot when performing the task. We next present an efficient algorithm for planning robot motions to perform the task based on the learned features while avoiding obstacles. We demonstrate the effectiveness of our motion planner for scenarios requiring transferring a powder and pushing a button in environments with obstacles, and we plan to extend our results to more complex tasks in the future.

show abstract

“…Another possible method is that a sampling database can be constructed to provide a statistical constraint on the selection of robotic arm configurations. For example, Claassens propose a robust algorithm to reproduce path that imitates prerecorded demonstration trajectories [16].…”

Section: The Hypothesis Of "Target Arm Pose" (Tap)mentioning

confidence: 99%

Human-like motion planning for robotic arm system

Xie

Zhao

Liu

2011

2011 15th International Conference on Advanced Robotics (ICAR)

View full text Add to dashboard Cite

We explore the problem of human-like motion planning for robotic arms based on researches in biophysics, robotics and motion planning. Two common manipulation tasks, reaching point movement in obstacle free environment and reaching point movement through a narrow passage, are separately studied. First, we proposed a hypothesis named "Target Arm Pose" (TAP) to interpret the natural motion of human arm. Second, based on TAPs and the minimum jerk model, we develop a new robotic inverse kinematic algorithm in joint jerk level to conduct the reaching point movement in obstacle free environment. Furthermore, based on the new algorithm we utilize the redundancy of the robot to avoid joint velocity limits. Next, we use existing Bi-RRT algorithm combined with TAPs to implement the reaching point movement through a narrow passage. Finally, comparison between these two tasks and two algorithms is made to give a systematic analysis on the human-like motion planning problem. ). J J X T T (6) By differentiating Eq.(6) once more with respect to time:Now suppose that the joint jerk T satisfying Eq. (7) exists, then Eq.(7) can be replaced by:where ( 2 ) J J J X

show abstract

An RRT-based path planner for use in trajectory imitation

Cited by 11 publications

References 13 publications

Demonstration-Guided Motion Planning

Demonstration-Guided Motion Planning

Asymptotically Optimal Motion Planning for Learned Tasks Using Time-Dependent Cost Maps

Human-like motion planning for robotic arm system

Contact Info

Product

Resources

About