Learn and Link: Learning Critical Regions for Efficient Planning

Molina, Daniel Antonio; Kumar, Kislay; Srivastava, Siddharth

doi:10.1109/icra40945.2020.9196833

Cited by 24 publications

(26 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In general, training network for motion planning requires a massive dataset, since a trajectory is generated by a sequence of control inputs. Therefore, many previous neural network approaches exploit successful trajectories by traditional motion planners to create training datasets [19]- [21], [23], [24]. However, all data samples are not equally important for the training of neural networks [26], [27].…”

Section: Related Workmentioning

confidence: 99%

Learning Continuous Cost-to-Go Functions for Non-holonomic Systems

Huh¹,

Lee²,

Isler³

2021

Preprint

View full text Add to dashboard Cite

This paper presents a supervised learning method to generate continuous cost-to-go functions of non-holonomic systems directly from the workspace description. Supervision from informative examples reduces training time and improves network performance. The manifold representing the optimal trajectories of a non-holonomic system has high-curvature regions which can not be efficiently captured with uniform sampling. To address this challenge, we present an adaptive sampling method which makes use of sampling based planners along with local, closed-form solutions to generate training samples. The cost-to-go function over a specific workspace is represented as a neural network whose weights are generated by a second, higher order network. The networks are trained in an end-to-end fashion. In our previous work, this architecture was shown to successfully learn to generate the cost-to-go functions of holonomic systems using uniform sampling. In this work, we show that uniform sampling fails for non-holonomic systems. However, with the proposed adaptive sampling methodology, our network can generate near-optimal trajectories for nonholonomic systems while avoiding obstacles. Experiments show that our method is two orders of magnitude faster compared to traditional approaches in cluttered environments.

show abstract

Section: Related Workmentioning

confidence: 99%

Learning Continuous Cost-to-Go Functions for Non-holonomic Systems

Huh¹,

Lee²,

Isler³

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…3) Criticality Test: Local primitives may or may not create "challenging regions," and finding if a configuration belongs to such a region is not straightforward. For example, the authors of [34] chose regions with maximum path density while [35] and [6] identified "challenging regions" using graph properties of a roadmap. To overcome this problem, we introduce training via a criticality test, which associates key configurations from solution paths to relevant local primitives.…”

Section: A Notation and Definitionsmentioning

confidence: 99%

Learning Sampling Distributions Using Local 3D Workspace Decompositions for Motion Planning in High Dimensions

Chamzas,

Kingston,

Quintero-Peña

et al. 2020

Preprint

View full text Add to dashboard Cite

Earlier work has shown that reusing experience from prior motion planning problems can improve the efficiency of similar, future motion planning queries. However, for robots with many degrees-of-freedom, these methods exhibit poor generalization across different environments and often require large datasets that are impractical to gather. We present SPARK and FLAME, two experience-based frameworks for samplingbased planning applicable to complex manipulators in D environments. Both combine samplers associated with features from a workspace decomposition into a global biased sampling distribution. SPARK decomposes the environment based on exact geometry while FLAME is more general, and uses an octree-based decomposition obtained from sensor data. We demonstrate the effectiveness of SPARK and FLAME on a Fetch robot tasked with challenging pick-and-place manipulation problems. Our approaches can be trained incrementally and significantly improve performance with only a handful of examples, generalizing better over diverse tasks and environments as compared to prior approaches.

show abstract

“…State-of-the-art motion planning algorithms such as PRM [17] and RRT [23] use random sampling of low-level configurations to compute a path from the robot's current location 𝐵1 to its target location 𝐾. Such sampling-based methods fail to efficiently sample configurations from confined spaces such as doorways and corridors under uniform sampling [29].…”

Section: Introductionmentioning

confidence: 99%

Using Deep Learning to Bootstrap Abstractions for Hierarchical Robot Planning

Shah¹,

Srivastava²

2022

Preprint

Self Cite

View full text Add to dashboard Cite

This paper addresses the problem of learning abstractions that boost robot planning performance while providing strong guarantees of reliability. Although state-of-the-art hierarchical robot planning algorithms allow robots to efficiently compute long-horizon motion plans for achieving user desired tasks, these methods typically rely upon environment-dependent state and action abstractions that need to be hand-designed by experts.We present a new approach for bootstrapping the entire hierarchical planning process. This allows us to compute abstract states and actions for new environments automatically using the critical regions predicted by a deep neural network with an auto-generated robot-specific architecture. We show that the learned abstractions can be used with a novel multi-source bi-directional hierarchical robot planning algorithm that is sound and probabilistically complete. An extensive empirical evaluation on twenty different settings using holonomic and non-holonomic robots shows that (a) our learned abstractions provide the information necessary for efficient multi-source hierarchical planning; and that (b) this approach of learning, abstractions, and planning outperforms state-of-the-art baselines by nearly a factor of ten in terms of planning time on test environments not seen during training.

show abstract

Learn and Link: Learning Critical Regions for Efficient Planning

Cited by 24 publications

References 12 publications

Learning Continuous Cost-to-Go Functions for Non-holonomic Systems

Learning Continuous Cost-to-Go Functions for Non-holonomic Systems

Learning Sampling Distributions Using Local 3D Workspace Decompositions for Motion Planning in High Dimensions

Using Deep Learning to Bootstrap Abstractions for Hierarchical Robot Planning

Contact Info

Product

Resources

About