Corpus ID: 201714753

Belief-Space Planning using Learned Models with Application to Underactuated Hands

  title={Belief-Space Planning using Learned Models with Application to Underactuated Hands},
  author={Andrew Kimmel and Avishai Sintov and Juntao Tan and Bowen Wen and Abdeslam Boularias and Kostas E. Bekris},
Acquiring a precise model is a challenging task for many important robotic tasks and systems including in-hand manipulation using underactuated, adaptive hands. Learning stochastic, data-driven models is a promising alternative as they provide not only a way to propagate forward the system dynamics, but also express the uncertainty present in the collected data. Therefore, such models enable planning in the space of state distributions, i.e., in the belief space. This paper proposes a planning… Expand

Figures and Tables from this paper

Motion Planning with Competency-Aware Transition Models for Underactuated Adaptive Hands
This work proposes to rather invest a portion of the training data in a critic model, trained to estimate the error of the transition model given a state and a sequence of future actions, along with information of past actions, to reformulate the cost function of an asymptotically optimal motion planner. Expand
Tools for Data-driven Modeling of Within-Hand Manipulation with Underactuated Adaptive Hands
This work provides the first large public dataset of real within-hand manipulation that facilitates building such models, along with baseline datadriven modeling results, and contributes ROS-based physics-engine model of such hands for independent data collection, experimentation and sim-to-reality transfer work. Expand
A Probabilistic Model for Planar Sliding of Objects with Unknown Material Properties: Identification and Robust Planning
The results show that this technique can not only identify accurately mass and friction coefficients of non-uniform heterogeneous objects, but can also be used to successfully slide an unknown object to the edge of a table and pick it up from there, without any human assistance or feedback. Expand
Learning to Transfer Dynamic Models of Underactuated Soft Robotic Hands
An upper bound on the Lyapunov exponent of a trained transition model is derived, and two approaches that make use of this insight show significant improvement over traditional fine-tuning. Expand
Inferring Time-delayed Causal Relations in POMDPs from the Principle of Independence of Cause and Mechanism
This paper introduces an algorithm for discovering implicit and delayed causal relations between events observed by a robot at regular or arbitrary times, with the objective of improvingExpand
Robust, Occlusion-aware Pose Estimation for Objects Grasped by Adaptive Hands
A depth-based framework for robust pose estimation and short response times for adaptive hands, which demonstrates the accuracy and computational efficiency of the framework when applied on challenging, highly-occluded scenarios for different object types. Expand
Partially-Observed Decoupled Data-based Control (POD2C) for Complex Robotic Systems
The efficacy of the developed method is shown by controlling complex high dimensional nonlinear robotic systems in the presence of model and sensing uncertainty and for which analytical models are either unavailable or inaccurate. Expand
se(3)-TrackNet: Data-driven 6D Pose Tracking by Calibrating Image Residuals in Synthetic Domains
This work proposes a data-driven optimization approach for long-term, 6D pose tracking, which aims to identify the optimal relative pose given the current RGB-D observation and a synthetic image conditioned on the previous best estimate and the object’s model. Expand


Path Planning for Within-Hand Manipulation over Learned Representations of Safe States
This work proposes a framework for tracking a desired path of an object held by an adaptive hand via within-hand manipulation that can handle objects of different weights without retraining, and successfully avoids undesirable states while minimizing the proposed cost function. Expand
SARSOP: Efficient Point-Based POMDP Planning by Approximating Optimally Reachable Belief Spaces
This work has developed a new point-based POMDP algorithm that exploits the notion of optimally reachable belief spaces to improve com- putational efficiency and substantially outperformed one of the fastest existing point- based algorithms. Expand
Rapidly-exploring Random Belief Trees for motion planning under uncertainty
  • A. Bry, N. Roy
  • Mathematics, Computer Science
  • 2011 IEEE International Conference on Robotics and Automation
  • 2011
The algorithm incrementally constructs a graph of trajectories through state space, while efficiently searching over candidate paths through the graph at each iteration results in a search tree in belief space that provably converges to the optimal path. Expand
Learning a State Transition Model of an Underactuated Adaptive Hand
This letter aims to learn a stochastic version of underactuated hands automatically from data with minimum user effort by identifying the dominant, sensible features required to express hand state transitions given quasi-static motions, thereby enabling the learning of a probabilistic transition model from recorded trajectories. Expand
Efficient and Asymptotically Optimal Kinodynamic Motion Planning via Dominance-Informed Regions
This paper introduces a new informed and asymptotically optimal kinodynamic motion planner, the Dominance-Informed Region Tree (DIRT), which balances exploration-exploitation tradeoffs without many explicit parameters. Expand
Deep visual foresight for planning robot motion
This work develops a method for combining deep action-conditioned video prediction models with model-predictive control that uses entirely unlabeled training data and enables a real robot to perform nonprehensile manipulation — pushing objects — and can handle novel objects not seen during training. Expand
The Importance of a Suitable Distance Function in Belief-Space Planning
This work indicates that the rarely used Wasserstein distance (also known as Earth Mover’s Distance) is a more suitable metric than the commonly used \(\mathtt{L1} \) and Kullback–Leibler (\(\Mathtt{KL} \)) for belief-space planning. Expand
The Belief Roadmap: Efficient Planning in Belief Space by Factoring the Covariance
When a mobile agent does not know its position perfectly, incorporating the predicted uncertainty of future position estimates into the planning process can lead to substantially better motionExpand
Navigation Planning in Probabilistic Roadmaps with Uncertainty
This paper shows how the situation where the obstacle positions are not precisely known can be represented as a POMDP, and shows that while too large to be solved with exact methods, approximate point based methods can provide a good quality solution. Expand
Asymptotically optimal sampling-based kinodynamic planning
Two new methods, STABLE_SPARSE_RRT (SST) and SST*, result from this analysis, which are asymptotically near-optimal and optimal, respectively, and are shown to converge fast to high-quality paths, while they maintain only a sparse set of samples, which makes them computationally efficient. Expand