Multilevel Motion Planning: A Fiber Bundle Formulation

Orthey, Andreas; Akbar, Sohaib; Toussaint, Marc

doi:10.48550/arxiv.2007.09435

Cited by 5 publications

(41 citation statements)

References 124 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Second, prioritization frameworks [3,10,58] can be used, where robots are ranked and planned in sequential order, while imposing the previously planned movements as constraints for the next robot. Solutions to single robots act as admissible heuristics [37], but backtracking in continuous spaces can often be time consuming. Several approaches exist to avoid backtracking, for example by analyzing start or goal conflicts [54] or biasing towards local minimum solutions [35].…”

Section: A Multi-robot Motion Planningmentioning

confidence: 99%

Long-Horizon Multi-Robot Rearrangement Planning for Construction Assembly

Hartmann¹,

Orthey²,

Driess³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Robotic assembly planning has the potential to profoundly change how buildings can be designed and created. It enables architects to explicitly account for the assembly process already during the design phase, and enables efficient building methods that profit from the robots' different capabilities. Previous work has addressed planning of robot assembly sequences and identifying the feasibility of architectural designs. This paper extends previous work by enabling assembly planning with large, heterogeneous teams of robots. We present a scalable planning system which enables parallelization of complex task and motion planning problems by iteratively solving smaller sub-problems. Combining optimization methods to solve for manipulation constraints with a sampling-based bi-directional space-time path planner enables us to plan cooperative multirobot manipulation with unknown arrival-times. Thus, our solver allows for completing sub-problems and tasks with differing timescales and synchronizes them effectively. We demonstrate the approach on multiple case-studies and on two long-horizon building assembly scenarios to show the robustness and scalability of our algorithm.

show abstract

Section: A Multi-robot Motion Planningmentioning

confidence: 99%

Long-Horizon Multi-Robot Rearrangement Planning for Construction Assembly

Hartmann¹,

Orthey²,

Driess³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Finally, MOTIONBENCHMAKER has already been used to create a diverse set of datasets suitable for learning-based methods [8], [43], for hyper-parameter tuning methods [44], for planning under uncertainty [45], for planning in partially observable environments [46] and for planning on different abstraction levels [5], [47].…”

Section: Example Usecasesmentioning

confidence: 99%

MotionBenchMaker: A Tool to Generate and Benchmark Motion Planning Datasets

Chamzas,

Quintero-Peña,

Kingston

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Recently, there has been a wealth of development in motion planning for robotic manipulation-new motion planners are continuously proposed, each with their own unique strengths and weaknesses. However, evaluating new planners is challenging and researchers often create their own ad-hoc problems for benchmarking, which is time-consuming, prone to bias, and does not directly compare against other state-of-the-art planners. We present MOTIONBENCHMAKER, an open-source tool to generate benchmarking datasets for realistic robot manipulation problems. MOTIONBENCHMAKER is designed to be an extensible, easyto-use tool that allows users to both generate datasets and benchmark them by comparing motion planning algorithms. Empirically, we show the benefit of using MOTIONBENCHMAKER as a tool to procedurally generate datasets which helps in the fair evaluation of planners. We also present a suite of 40 prefabricated datasets, with 5 different commonly used robots in 8 environments, to serve as a common ground to accelerate motion planning research.

show abstract

“…In previous work, we and other research teams have shown that we can often efficiently solve high-dimensional planning problems by using admissible lower-dimensional projections of the state space, a topic we refer to as multilevel motion planning [22,5,67,75,97]. When using a multilevel motion planning framework, we can often use solutions to simplified planning stages as admissible heuristics for the original problem [70,1].…”

Section: Introductionmentioning

confidence: 99%

“…When using a multilevel motion planning framework, we can often use solutions to simplified planning stages as admissible heuristics for the original problem [70,1]. To efficiently exploit those admissible heuristics, we can use biased sampling methods [67,74], which we can combine with classical planning algorithms like the rapidly-exploring random tree algorithm [63], the probabilistic roadmap planner [65], its optimal star versions [67] or the fast marching trees planner [74]. However, while showing promising runtimes, those algorithms are prone to get trapped when run on problems involving narrow passages.…”

Section: Introductionmentioning

confidence: 99%

“…We introduce four section patterns. First, we introduce the Manhattan pattern, which we use to compute solution paths which actuate the minimal amount of joints to reach a goal region, which is advantageous for high dimensional systems [14,67]. Second, we introduce the Wriggle pattern, which we use to make small random walk steps to traverse a narrow passage.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Section Patterns: Efficiently Solving Narrow Passage Problems in Multilevel Motion Planning

Orthey¹,

Toussaint²

2020

Preprint

Self Cite

View full text Add to dashboard Cite

Sampling-based planning methods often become inefficient due to narrow passages. Narrow passages induce a higher runtime, because the chance to sample them becomes vanishingly small. In recent work, we showed that narrow passages can be approached by relaxing the problem using admissible lowerdimensional projections of the state space. Those relaxations often increase the volume of narrow passages under projection. Solving the relaxed problem is often efficient and produces an admissible heuristic we can exploit. However, given a base path, i.e. a solution to a relaxed problem, there are currently no tailored methods to efficiently exploit the base path. To efficiently exploit the base path and thereby its admissible heuristic, we develop section patterns, which are solution strategies to efficiently exploit base paths in particular around narrow passages. To coordinate section patterns, we develop the pattern dance algorithm, which efficiently coordinates section patterns to reactively traverse narrow passages. We combine the pattern dance algorithm with previously developed multilevel planning algorithms and benchmark them on challenging planning problems like the Bugtrap, the double L-shape, an egress problem and on four pregrasp scenarios for a 37 degrees of freedom shadow hand mounted on a KUKA LWR robot. Our results confirm that section patterns are useful to efficiently solve high-dimensional narrow passage motion planning problems.

show abstract

Multilevel Motion Planning: A Fiber Bundle Formulation

Cited by 5 publications

References 124 publications

Long-Horizon Multi-Robot Rearrangement Planning for Construction Assembly

Long-Horizon Multi-Robot Rearrangement Planning for Construction Assembly

MotionBenchMaker: A Tool to Generate and Benchmark Motion Planning Datasets

Section Patterns: Efficiently Solving Narrow Passage Problems in Multilevel Motion Planning

Contact Info

Product

Resources

About