Learning When to Trust a Dynamics Model for Planning in Reduced State Spaces

  title={Learning When to Trust a Dynamics Model for Planning in Reduced State Spaces},
  author={Dale Mcconachie and Thomas Power and P. Mitrano and Dmitry Berenson},
  journal={IEEE Robotics and Automation Letters},
When the dynamics of a system are difficult to model and/or time-consuming to evaluate, such as in deformable object manipulation tasks, motion planning algorithms struggle to find feasible plans efficiently. Such problems are often reduced to state spaces where the dynamics are straightforward to model and evaluate. However, such reductions usually discard information about the system for the benefit of computational efficiency, leading to cases where the true and reduced dynamics disagree on… 

Learning where to trust unreliable models in an unstructured world for deformable object manipulation

An approach is reported that learns a model in an unconstrained setting and then learns a classifier to predict where that model is valid, given a limited dataset of rope-constraint interactions, which statistically significantly outperforms learning a dynamics function and trusting it everywhere.

CMAX++ : Leveraging Experience in Planning and Execution using Inaccurate Models

CMAX++ is proposed, an approach that leverages real-world experience to improve the quality of resulting plans over successive repetitions of a robotic task and achieves this by integrating model-free learning using acquired experience with model-based planning using the potentially inaccurate model.

Keep It Simple: Data-Efficient Learning for Controlling Complex Systems With Simple Models

The proposed Learned Visual Similarity Predictive Control (LVSPC), a novel method for data-efficient learning to control systems with complex dynamics and high-dimensional state spaces from images, performs comparably to state-of-the-art reinforcement learning methods with an order of magnitude less data.

Planning with Learned Dynamics: Guaranteed Safety and Reachability via Lipschitz Constants

An approach for feedback motion planning of systems with unknown dynamics which provides guarantees on safety, reachability, and stability about the goal and shows that a baseline which plans using the same learned dynamics without considering the error bound or the existence of the feedback law can fail to stabilize around the plan and become unsafe.

Planning With Learned Dynamics: Probabilistic Guarantees on Safety and Reachability via Lipschitz Constants

This work imposes the feedback law existence as a constraint in a sampling-based planner which returns a feedback policy around a nominal plan ensuring that, if the Lipschitz constant estimate is valid, the true system is safe during plan execution, reaches the goal, and is ultimately invariant in a small set about the goal.

Planning and Execution using Inaccurate Models with Provable Guarantees

This paper proposes CMAX an approach for interleaving planning and execution that adapts its planning strategy online during real-world execution to account for any discrepancies in dynamics during planning, without requiring updates to the dynamics of the model.

Differentiable Robotic Manipulation of Deformable Rope-like Objects Using Compliant Position-based Dynamics

Robot manipulation of rope-like objects is an interesting problem that has some critical applications, such as autonomous robotic suturing. Solving for and controlling rope is difficult due to the

Shape Control of Deformable Linear Objects with Offline and Online Learning of Local Linear Deformation Models

A scheme for the shape control of DLOs, where the unknown model is estimated with both offline and online learning, and formulated in a local linear format, and approximated by a neural network.

Challenges and Outlook in Robotic Manipulation of Deformable Objects

This article reviews recent advances in deformable object manipulation and highlights the main challenges when considering deformation in each sub-field, and proposes future directions of research.

A Survey on the Integration of Machine Learning with Sampling-based Motion Planning

This survey discusses how learning has been used to enhance key components of SBMPs, such as node sampling, collision detection, distance or nearest neighbor computation, local and a classification of the alternative directions that have been explored in the literature.