Enabling Fixtureless Assemblies in Human-Robot Collaborative Workcells by Reducing Uncertainty in the Part Pose Estimate

2020 IEEE 16th International Conference on Automation Science and Engineering (CASE)

Balakrishna

et al. 2020

Orienting objects is a critical component in the automation of many packing and assembly tasks. We present an algorithm to orient novel objects given a depth image of the object in its current and desired orientation. We formulate a self-supervised objective for this problem and train a deep neural network to estimate the 3D rotation as parameterized by a quaternion, between these current and desired depth images. We then use the trained network in a proportional controller to re-orient objects based on the estimated rotation between the two depth images. Results suggest that in simulation we can rotate unseen objects with unknown geometries by up to 30°with a median angle error of 1.47°over 100 random initial/desired orientations each for 22 novel objects. Experiments on physical objects suggest that the controller can achieve a median angle error of 4.2°over 10 random initial/desired orientations each for 5 objects.

show abstract

Section: Related Workmentioning

confidence: 99%

Orienting Novel 3D Objects Using Self-Supervised Learning of Rotation Transforms

2020 IEEE 16th International Conference on Automation Science and Engineering (CASE)

Balakrishna

et al. 2020

show abstract

“…Akella et al [1] extend the work of Goldberg with sensor-based and sensor-less algorithms for orienting objects with known geometry and shape variation. Kumbla et al [12] propose a method for estimating object pose via computer vision and then reorient the object using active probing. Leveroni et al [13] optimize robot finger motions to reorient a known convex object while maintaining grasp stability.…”

Section: Related Workmentioning

confidence: 99%

Kit-Net: Self-Supervised Learning to Kit Novel 3D Objects into Novel 3D Cavities

Danielczuk

et al. 2021

Preprint

In industrial part kitting, 3D objects are inserted into cavities for transportation or subsequent assembly. Kitting is a critical step as it can decrease downstream processing and handling times and enable lower storage and shipping costs. We present Kit-Net, a framework for kitting previously unseen 3D objects into cavities given depth images of both the target cavity and an object held by a gripper in an unknown initial orientation. Kit-Net uses self-supervised deep learning and dataaugmentation to train a convolutional neural network (CNN) to robustly estimate 3D rotations between objects and matching concave or convex cavities using a large training dataset of simulated depth images pairs. Kit-Net then uses the trained CNN to implement a controller to orient and position novel objects for insertion into novel prismatic and conformal 3D cavities. Experiments in simulation suggest that Kit-Net can orient objects to have a 98.9 % average intersection volume between the object mesh and that of the target cavity. Physical experiments with industrial objects succeed in 18 % of trials using a baseline method and in 63 % of trials with Kit-Net. Video, code, and data are available at https://github. com/BerkeleyAutomation/Kit-Net.

show abstract

Kit-Net: Self-Supervised Learning to Kit Novel 3D Objects into Novel 3D Cavities

2021 IEEE 17th International Conference on Automation Science and Engineering (CASE)

Danielczuk

et al. 2021