Robot grasping of deformable hollow objects such as plastic bottles and cups is challenging, as the grasp should resist disturbances while minimally deforming the object so as not to damage it or dislodge liquids. We propose minimal work as a novel grasp quality metric that combines wrench resistance and object deformation. We introduce an efficient algorithm to compute the work required to resist an external wrench for a manipulation task by solving a linear program. The algorithm first computes the minimum required grasp force and an estimation of the gripper jaw displacements based on the object's empirical stiffness at different locations. The work done by the jaws is the product of the grasp force and the displacements. Grasps requiring minimal work are considered to be of high quality. We collect 460 physical grasps with a UR5 robot and a Robotiq gripper. We consider a grasp to be successful if it completes the task without damaging the object or dislodging the content. Physical experiments suggest that the minimal work quality metric reaches 74.2% balanced accuracy, a metric that is the raw accuracy normalized by the number of successful and failed real-world grasps, and is up to 24.2% higher than classical wrench-based quality metrics.

The ability to segment unknown objects in depth images has potential to enhance robot skills in grasping and object tracking. Recent computer vision research has demonstrated that Mask R-CNN can be trained to segment specific categories of objects in RGB images when massive hand-labeled datasets are available. As generating these datasets is time-consuming, we instead train with synthetic depth images. Many robots now use depth sensors, and recent results suggest training on synthetic depth data can transfer successfully to the real world. We present a method for automated dataset generation and rapidly generate a synthetic training dataset of 50,000 depth images and 320,000 object masks using simulated heaps of 3D CAD models. We train a variant of Mask R-CNN with domain randomization on the generated dataset to perform category-agnostic instance segmentation without any hand-labeled data and we evaluate the trained network, which we refer to as Synthetic Depth (SD) Mask R-CNN, on a set of real, high-resolution depth images of challenging, densely-cluttered bins containing objects with highly-varied geometry. SD Mask R-CNN outperforms point cloud clustering baselines by an absolute 15% in Average Precision and 20% in Average Recall on COCO benchmarks, and achieves performance levels similar to a Mask R-CNN trained on a massive, hand-labeled RGB dataset and fine-tuned on real images from the experimental setup. We deploy the model in an instance-specific grasping pipeline to demonstrate its usefulness in a robotics application. Code, the synthetic training dataset, and supplementary material are available at https://bit.ly/2letCuE.

Caging grasps limit the mobility of an object to a bounded component of configuration space. We introduce a notion of partial cage quality based on maximal clearance of an escaping path. As this is a computationally demanding task even in a two-dimensional scenario, we propose a deep learning approach. We design two convolutional neural networks and construct a pipeline for real-time partial cage quality estimation directly from 2D images of object models and planar caging tools. One neural network, CageMaskNN, is used to identify caging tool locations that can support partial cages, while a second network that we call CageClearanceNN is trained to predict the quality of those configurations. A dataset of 3811 images of objects and more than 19 million caging tool configurations is used to train and evaluate these networks on previously unseen objects and caging tool configurations. Furthermore, the networks are trained jointly on configurations for both 3 and 4 caging tool configurations whose shape varies along a 1-parameter family of increasing elongation. In experiments, we study how the networks' performance depends on the size of the training dataset, as well as how to efficiently deal with unevenly distributed training data. In further analysis, we show that the evaluation pipeline can approximately identify connected regions of successful caging tool placements and we evaluate the continuity of the cage quality score evaluation along caging tool trajectories. Experiments show that evaluation of a given configuration on a GeForce GTX 1080 GPU takes less than 6 ms.

Vacuum-based end effectors are widely used in industry and are often preferred over parallel-jaw and multifinger grippers due to their ability to lift objects with a single point of contact. Suction grasp planners often target planar surfaces on point clouds near the estimated centroid of an object. In this paper, we propose a compliant suction contact model that computes the quality of the seal between the suction cup and local target surface and a measure of the ability of the suction grasp to resist an external gravity wrench. To characterize grasps, we estimate robustness to perturbations in end-effector and object pose, material properties, and external wrenches. We analyze grasps across 1,500 3D object models to generate Dex-Net 3.0, a dataset of 2.8 million point clouds, suction grasps, and grasp robustness labels. We use Dex-Net 3.0 to train a Grasp Quality Convolutional Neural Network (GQ-CNN) to classify robust suction targets in point clouds containing a single object. We evaluate the resulting system in 350 physical trials on an ABB YuMi fitted with a pneumatic suction gripper. When evaluated on novel objects that we categorize as Basic (prismatic or cylindrical), Typical (more complex geometry), and Adversarial (with few available suction-grasp points) Dex-Net 3.0 achieves success rates of 98%, 82%, and 58% respectively, improving to 81% in the latter case when the training set includes only adversarial objects. Code, datasets, and supplemental material can be found at http://berkeleyautomation.github.io/dex-net.

For applications such as manufacturing, caging grasps restrict object motion without requiring complete immobilization, providing a robust alternative to forceand form-closure grasps. Energy-bounded cages are a new class of caging grasps that relax the requirement of complete caging in the presence of external forces such as gravity or constant velocity pushing in the horizontal plane with Coulomb friction. We address the problem of synthesizing planar energy-bounded cages by identifying gripper and force-direction configurations that maximize the energy required for the object to escape. We present Energy-BoundedCage-Synthesis-2-D (EBCS-2-D), a sampling-based algorithm that uses persistent homology, a recently-developed multiscale approach for topological analysis, to efficiently compute candidate rigid configurations of obstacles that form energy-bounded cages of an object from an α-shape approximation to the configuration space. If a synthesized configuration has infinite escape energy then the object is completely caged. EBCS-2-D runs in O(s3+ sn2) time, where s is the number of samples and n is the number of object and obstacle vertices, where typically n ≪ s. We observe runtimes closer to O(s) for fixed n. We implement EBCS-2-D using the persistent homology algorithms toolbox and study performance on a set of seven planar objects and four gripper types. Experiments suggest that EBCS-2-D takes 2-3 min on a 6 core processor with 200000 pose samples. We also confirm that an rapidly-exploring random tree* motion planner is unable to find escape paths with lower energy. Physical experiments on a five degree of freedom Zymark Zymate and ABB YuMi suggest that push grasps synthesized by EBCS-2-D are robust to perturbations. Data and code are available at http://berkeleyautomation.github.io/caging/.

Automated grasping has a long history of research that is increasing due to interest from industry. One grand challenge for robotics is Universal Picking: the ability to robustly grasp a broad variety of objects in diverse environments for applications from warehouses to assembly lines to homes. Although many researchers now openly share code and data, it is challenging to compare and/or reproduce experimental results to identify which aspects of which approaches work best due to variations in assumptions and experimental protocols, e.g., sensors, lighting, robot arms, grippers, and objects.

Parallel-jaw robot grippers can grasp almost any object and are ubiquitous in industry. Although the shape, texture, and compliance of gripper jaw surfaces affect grasp robustness, almost all commercially available grippers provide a pair of rectangular, planar, rigid jaw surfaces. Practitioners often modify these surfaces with a variety of ad-hoc methods such as adding rubber caps and/or wrapping with textured tape. This paper explores data-driven optimization of gripper jaw surfaces over a design space based on shape, texture, and compliance using rapid prototyping. In total, 37 jaw surface design variations were created using 3D printed casting molds and silicon rubber. The designs were evaluated with 1377 physical grasp experiments using a 4-axis robot (with automated reset). These tests evaluate grasp robustness as the probability that the jaws will acquire, lift, and hold a training set of objects at nominal grasp configurations computed by Dex-Net 1.0. Hill-climbing in parameter space yielded a grid pattern of 0.03 inch void depth and 0.0375 inch void width on a silicone polymer with durometer of A30. We then evaluated performance of this design using an ABB YuMi robot grasping a set of eight difficult-to-grasp 3D printed objects in 80 grasps with four gripper surfaces. The factory-provided gripper tips succeeded in 28.7% of the 80 trials, increasing to 68.7% when the tips were wrapped with tape. Gripper tips with gecko-inspired surfaces succeeded in 80.0% of trials, and gripper tips with the designed silicone surfaces succeeded in 93.7% of trials.

Motivated by recent advances in Deep Learning for robot control, this paper considers two learning algorithms in terms of how they acquire demonstrations from fallible human supervisors. Human-Centric (HC) sampling is a standard supervised learning algorithm, where a human supervisor demonstrates the task by teleoperating the robot to provide trajectories consisting of state-control pairs. Robot-Centric (RC) sampling is an increasingly popular alternative used in algorithms such as DAgger, where a human supervisor observes the robot execute a learned policy and provides corrective control labels for each state visited. We suggest RC sampling can be challenging for human supervisors and prone to mislabeling. RC sampling can also induce error in policy performance because it repeatedly visits areas of the state space that are harder to learn. Although policies learned with RC sampling can be superior to HC sampling for standard learning models such as linear SVMs, policies learned with HC sampling may be comparable to RC when applied to expressive learning models such as deep learning and hyper-parametric decision trees, which can achieve very low training error provided there is enough data. We compare HC and RC using a grid world environment and a physical robot singulation task. In the latter the input is a binary image of objects on a planar worksurface and the policy generates a motion in the gripper to separate one object from the rest. We observe in simulation that for linear SVMs, policies learned with RC outperformed those learned with HC but that using deep models this advantage disappears. We also find that with RC, the corrective control labels provided by humans can be highly inconsistent. We prove there exists a class of examples in which at the limit, HC is guaranteed to converge to an optimal policy while RC may fail to converge. These results suggest a form of HC sampling may be preferable for highly-expressive learning models and human supervisors.

In support of Cloud Robotics, Robotics and Automation as a Service (RAaaS) frameworks have the potential to reduce the complexity of software development, simplify software installation and maintenance, and facilitate data sharing for machine learning. In this proof-of-concept paper, we describe Berkeley Robotics and Automation as a Service (Brass), a RAaaS prototype that allows robots to access a remote server that hosts a robust grasp-planning system (Dex-Net 1.0) that maintains data on hundreds of candidate grasps on thousands of 3D object meshes and uses perturbation sampling to estimate and update a stochastic robustness metric for each grasp. Results suggest that such a system can increase grasp reliability over naive locally-computed grasping strategies with network latencies of 30 and 200 msec for servers 500 and 6000 miles away, respectively. We also study how the system can use execution reports from robots in the field to update grasp recommendations over time.

Online learning from demonstration algorithms such as DAgger can learn policies for problems where the system dynamics and the cost function are unknown. However they impose a burden on supervisors to respond to queries each time the robot encounters new states while executing its current best policy. The MMD-IL algorithm reduces supervisor burden by filtering queries with insufficient discrepancy in distribution and maintaining multiple policies. We introduce the SHIV algorithm (Svm-based reduction in Human InterVention), which converges to a single policy and reduces supervisor burden in non-stationary high dimensional state distributions. To facilitate scaling and outlier rejection, filtering is based on a measure of risk defined in terms of distance to an approximate level set boundary defined by a One Class support vector machine. We report on experiments in three contexts: 1) a driving simulator with a 27,936 dimensional visual feature space, 2) a push-grasping in clutter simulation with a 22 dimensional state space, and 3) physical surgical needle insertion with a 16 dimensional state space. Results suggest that SHIV can efficiently learn policies with up to 70% fewer queries that DAgger.

This paper presents the Dexterity Network (Dex-Net) 1.0, a dataset of 3D object models and a sampling-based planning algorithm to explore how Cloud Robotics can be used for robust grasp planning. The algorithm uses a Multi- Armed Bandit model with correlated rewards to leverage prior grasps and 3D object models in a growing dataset that currently includes over 10,000 unique 3D object models and 2.5 million parallel-jaw grasps. Each grasp includes an estimate of the probability of force closure under uncertainty in object and gripper pose and friction. Dex-Net 1.0 uses Multi-View Convolutional Neural Networks (MV-CNNs), a new deep learning method for 3D object classification, to provide a similarity metric between objects, and the Google Cloud Platform to simultaneously run up to 1,500 virtual cores, reducing experiment runtime by up to three orders of magnitude. Experiments suggest that correlated bandit techniques can use a cloud-based network of object models to significantly reduce the number of samples required for robust grasp planning. We report on system sensitivity to variations in similarity metrics and in uncertainty in pose and friction. Code and updated information is available at http://berkeleyautomation.github.io/dex-net/.

Computing grasps for an object is challenging when the object geometry is not known precisely. In this paper, we explore the use of Gaussian process implicit surfaces (GPISs) to represent shape uncertainty from RGBD point cloud observations of objects. We study the use of GPIS representations to select grasps on previously unknown objects, measuring grasp quality by the probability of force closure. Our main contribution is GP-GPIS-OPT, an algorithm for computing grasps for parallel-jaw grippers on 2D GPIS object representations. Specifically, our method optimizes an approximation to the probability of force closure subject to antipodal constraints on the parallel jaws using Sequential Convex Programming (SCP). We also introduce GPIS-Blur, a method for visualizing 2D GPIS models based on blending shape samples from a GPIS. We test the algorithm on a set of 8 planar objects with transparency, translucency, and specularity. Our experiments suggest that GP-GPIS-OPT computes grasps with higher probability of force closure than a planner that does not consider shape uncertainty on our test objects and may converge to a grasp plan up to 5.7×faster than using Monte-Carlo integration, a common method for grasp planning under shape uncertainty. Furthermore, initial experiments on the Willow Garage PR2 robot suggest that grasps selected with GP-GPIS-OPT are up to 90% more successful than those planned assuming a deterministic shape. Our dataset, code, and videos of our experiments are available at http://rll.berkeley.edu/icra2015grasping/.

Autonomous robot execution of surgical sub-tasks has the potential to reduce surgeon fatigue and facilitate supervised tele-surgery. This paper considers the sub-task of surgical debridement: removing dead or damaged tissue fragments to allow the remaining healthy tissue to heal. We present an autonomous multilateral surgical debridement system using the Raven, an open-architecture surgical robot with two cable-driven 7 DOF arms. Our system combines stereo vision for 3D perception with trajopt, an optimization-based motion planner, and model predictive control (MPC). Laboratory experiments involving sensing, grasping, and removal of 120 fragments suggest that an autonomous surgical robot can achieve robustness comparable to human performance. Our robot system demonstrated the advantage of multilateral systems, as the autonomous execution was 1.5× faster with two arms than with one; however, it was two to three times slower than a human. Execution speed could be improved with better state estimation that would allow more travel between MPC steps and fewer MPC replanning cycles. The three primary contributions of this paper are: (1) introducing debridement as a sub-task of interest for surgical robotics, (2) demonstrating the first reliable autonomous robot performance of a surgical sub-task using the Raven, and (3) reporting experiments that highlight the importance of accurate state estimation for future research. Further information including code, photos, and video is available at: http://rll.berkeley.edu/raven.