There has been significant recent work on data-driven algorithms for learning general-purpose grasping policies. However, these policies can consis- tently fail to grasp challenging objects which are significantly out of the distribution of objects in the training data or which have very few high quality grasps. Moti- vated by such objects, we propose a novel problem setting, Exploratory Grasping, for efficiently discovering reliable grasps on an unknown polyhedral object via sequential grasping, releasing, and toppling. We formalize Exploratory Grasping as a Markov Decision Process where we assume that the robot can (1) distinguish stable poses of a polyhedral object of unknown geometry, (2) generate grasp can- didates on these poses and execute them, (3) determine whether each grasp is successful, and (4) release the object into a random new pose after a grasp success or topple the object after a grasp failure. We study the theoretical complexity of Exploratory Grasping in the context of reinforcement learning and present an efficient bandit-style algorithm, Bandits for Online Rapid Grasp Exploration Strategy (BORGES), which leverages the structure of the problem to efficiently discover high performing grasps for each object stable pose. BORGES can be used to complement any general-purpose grasping algorithm with anymore »
Formulation and Validation of an Intuitive Quality Measure for Antipodal Grasp Pose Evaluation
Practical robot applications that require grasping often fail due to failed grasp planning, and a good grasp quality measure is the key to successful grasp planning. In this paper, we developed a novel grasp quality measure that quantifies and evaluates grasp quality in real-time. To quantify the grasp quality, we compute a set of object movement features from analyzing the interaction between the gripper and the object’s projections in the image space. The normalizations and weights of the features are tuned to make practical and intuitive grasp quality predictions. To evaluate our grasp quality measure, we conducted a real robot grasping experiment with 1000 robot grasp trials on ten household objects to examine the relationship between our grasp scores and the actual robot grasping results. The results show that the average grasp success rate increases, and the average amount of undesired object movement decrease as the calculated grasp score increases, which validates our quality measure. We achieved a 100% grasp success rate from 100 grasps of the ten objects when using our grasp quality measure in planning top quality grasps.
- Award ID(s):
- Publication Date:
- NSF-PAR ID:
- Journal Name:
- Proceedings of the IEEERSJ International Conference on Intelligent Robots and Systems
- Sponsoring Org:
- National Science Foundation
More Like this
Grasping in dynamic environments presents a unique set of challenges. A stable and reachable grasp can become unreachable and unstable as the target object moves, motion planning needs to be adaptive and in real time, the delay in computation makes prediction necessary. In this paper, we present a dynamic grasping framework that is reachabilityaware and motion-aware. Specifically, we model the reachability space of the robot using a signed distance field which enables us to quickly screen unreachable grasps. Also, we train a neural network to predict the grasp quality conditioned on the current motion of the target. Using these as ranking functions, we quickly filter a large grasp database to a few grasps in real time. In addition, we present a seeding approach for arm motion generation that utilizes solution from previous time step. This quickly generates a new arm trajectory that is close to the previous plan and prevents fluctuation. We implement a recurrent neural network (RNN) for modelling and predicting the object motion. Our extensive experiments demonstrate the importance of each of these components and we validate our pipeline on a real robot.
Robotic grasping is successful when a robot can sense and grasp an object without letting it slip. Beyond industrial robotic tasks, there are two main robotic grasping methods. The first is planning-based grasping where the object geometry is known beforehand and stable grasps are calculated using algorithms . The second uses tactile feedback. Currently, there are capacitive sensors placed beneath stiff pads on the front of robotic fingers . With post-execution grasp adjustment procedures to estimate grasp stability, a support vector machine classifier can distinguish stable and unstable grasps. The accuracy across the classes of tested objects is 81% . We are proposing to improve the classifier's accuracy by wrapping flexible sensors around the robotic finger to gain information from the edges and sides of the finger.
Generative Attention Learning: a “GenerAL” framework for high-performance multi-fingered grasping in clutterGenerative Attention Learning (GenerAL) is a framework for high-DOF multi-fingered grasping that is not only robust to dense clutter and novel objects but also effective with a variety of different parallel-jaw and multi-fingered robot hands. This framework introduces a novel attention mechanism that substantially improves the grasp success rate in clutter. Its generative nature allows the learning of full-DOF grasps with flexible end-effector positions and orientations, as well as all finger joint angles of the hand. Trained purely in simulation, this framework skillfully closes the sim-to-real gap. To close the visual sim-to-real gap, this framework uses a single depth image as input. To close the dynamics sim-to-real gap, this framework circumvents continuous motor control with a direct mapping from pixel to Cartesian space inferred from the same depth image. Finally, this framework demonstrates inter-robot generality by achieving over 92% real-world grasp success rates in cluttered scenes with novel objects using two multi-fingered robotic hand-arm systems with different degrees of freedom.
Robot manipulation and grasping mechanisms have received considerable attention in the recent past, leading to development of wide-range of industrial applications. This paper proposes the development of an autonomous robotic grasping system for object sorting application. RGB-D data is used by the robot for performing object detection, pose estimation, trajectory generation and object sorting tasks. The proposed approach can also handle grasping on certain objects chosen by users. Trained convolutional neural networks are used to perform object detection and determine the corresponding point cloud cluster of the object to be grasped. From the selected point cloud data, a grasp generator algorithm outputs potential grasps. A grasp filter then scores these potential grasps, and the highest-scored grasp will be chosen to execute on a real robot. A motion planner will generate collision-free trajectories to execute the chosen grasp. The experiments on AUBO robotic manipulator show the potentials of the proposed approach in the context of autonomous object sorting with robust and fast sorting performance.