Grasp Planning for Customized Grippers by Iterative Surface Fitting

Yi, Fan; Lin, Hsien-Chung; Tian, Tao; Tomizuka, Masayoshi

doi:10.1109/coase.2018.8560361

Cited by 18 publications

(21 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Compared with non-rigid registration [16], MDISF only deforms in the feasible directions of the joint motion. Compared with the ISF algorithm [10], MDISF is able to plan grasps for the hands with multiple DOFs, and the collision between the hand and the object/ground is penalized directly in the optimization.…”

Section: The General Planning Frameworkmentioning

confidence: 99%

“…The guided sampling is introduced to avoid being trapped in bad-performed local optima by prioritizing different initial palm placements, so that the regions with smaller fitting errors and better collision avoidance performance can be sampled more often. The detail of the guided sampling is in [10].…”

Section: The General Planning Frameworkmentioning

confidence: 99%

“…To avoid excessive hand-engineering, we proposed a grasp planning method called iterative surface fitting (ISF) in [10] and increased the efficiency by combining with learning in [11]. ISF optimized for both the palm pose and finger displacements by maximizing the surface fitting score.…”

Section: Introductionmentioning

confidence: 99%

“…By optimizing the palm pose and finger joints iteratively, the planning algorithm is able to implement on the hands with multiple DOFs. Secondly, the collision is penalized by the gradient-based methods directly, instead of being pruned after optimization as [10]. Furthermore, the proposed method can generate both the power grasps and precision grasps by adjusting the fitting weights of fingertips.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Efficient Grasp Planning and Execution With Multifingered Hands by Surface Fitting

Tomizuka

2019

IEEE Robot. Autom. Lett.

Self Cite

View full text Add to dashboard Cite

This paper introduces a framework to plan grasps with multi-fingered hands. The framework includes a multidimensional iterative surface fitting (MDISF) for grasp planning and a grasp trajectory optimization (GTO) for grasp imagination. The MDISF algorithm searches for optimal contact regions and hand configurations by minimizing the collision and surface fitting error, and the GTO algorithm generates optimal finger trajectories to reach the highly ranked grasp configurations and avoid collision with the environment. The proposed grasp planning and imagination framework considers the collision avoidance and the kinematics of the hand-robot system, and is able to plan grasps and trajectories of different categories efficiently with gradient-based methods using the captured point cloud. The found grasps and trajectories are robust to sensing noises and underlying uncertainties. The effectiveness of the proposed framework is verified by both simulations and experiments. The experimental videos are available at [1].

show abstract

Section: The General Planning Frameworkmentioning

confidence: 99%

Section: The General Planning Frameworkmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Efficient Grasp Planning and Execution With Multifingered Hands by Surface Fitting

Tomizuka

2019

IEEE Robot. Autom. Lett.

Self Cite

View full text Add to dashboard Cite

show abstract

“…The guided sampling in the outer loop is introduced from [12] to avoid the iterative PPO-JPO being trapped in poor-performed local optima. It employs the K-means clustering of the object surface and places the hand onto the cluster centers.…”

Section: Frameworkmentioning

confidence: 99%

optimization Model for Planning Precision Grasps with Multi-Fingered Hands

Zhu

Tomizuka

2019

2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

Self Cite

View full text Add to dashboard Cite

Precision grasps with multi-fingered hands are important for precise placement and in-hand manipulation tasks. Searching precision grasps on the object represented by point cloud, is challenging due to the complex object shape, high-dimensionality, collision and undesired properties of the sensing and positioning. This paper proposes an optimization model to search for precision grasps with multi-fingered hands. The model takes noisy point cloud of the object as input and optimizes the grasp quality by iteratively searching for the palm pose and finger joints positions. The collision between the hand and the object is approximated and penalized by a series of least-squares. The collision approximation is able to handle the point cloud representation of the objects with complex shapes. The proposed optimization model is able to locate collision-free optimal precision grasps efficiently. The average computation time is 0.50 sec/grasp. The searching is robust to the incompleteness and noise of the point cloud. The effectiveness of the algorithm is demonstrated by experiments. The experimental video is available at [1].

show abstract