Using Simulation and Domain Adaptation to Improve Efficiency of Deep Robotic Grasping
Google Brain（谷歌大脑）
Konstantinos Bousmalis, Alex Irpan, Paul Wohlhart, Yunfei Bai, Matthew Kelcey, Mrinal Kalakrishnan, Laura Downs, Julian Ibarz, Peter Pastor, Kurt Konolige, Serg… 展开作者
Konstantinos Bousmalis, Alex Irpan, Paul Wohlhart, Yunfei Bai, Matthew Kelcey, Mrinal Kalakrishnan, Laura Downs, Julian Ibarz, Peter Pastor, Kurt Konolige, Sergey Levine, Vincent Vanhoucke
Instrumenting and collecting annotated visual grasping datasets to train modern machine learning algorithms can be extremely time-consuming and expensive. An appealing alternative is to use off-the-shelf simulators to render synthetic data for which ground-truth annotations are generated automatically. Unfortunately, models trained purely on simulated data often fail to generalize to the real world. We study how randomized simulated environments and domain adaptation methods can be extended to train a grasping system to grasp novel objects from raw monocular RGB images. We extensively evaluate our approaches with a total of more than 25,000 physical test grasps, studying a range of simulation conditions and domain adaptation methods, including a novel extension of pixel-level domain adaptation that we term the GraspGAN. We show that, by using synthetic data and domain adaptation, we are able to reduce the number of real-world samples needed to achieve a given level of performance by up to 50 times, using only randomly generated simulated objects. We also show that by using only unlabeled real-world data and our GraspGAN methodology, we obtain real-world grasping performance without any real-world labels that is similar to that achieved with 939,777 labeled real-world samples.
Learning-based approaches to robotic manipulation are limited by the scalability of data collection and accessibility of labels. In this paper, we present a multi-task domain adaptation framework for instance grasping in cluttered scenes by utilizing simulated robot experiments. Our neural network takes monocular RGB images and the instance segmentation mask of a specified target object as inputs, and predicts the probability of successfully grasping the specified object for each candidate motor command. The proposed transfer learning framework trains a model for instance grasping in simulatio…
Universität Hamburg（汉堡大学）；Agile Robots AG（敏捷机器人公司）
Precise robotic grasping of several novel objects is a huge challenge in manufacturing, automation, and logistics. Most of the current methods for model-free grasping are disadvantaged by the sparse data in grasping datasets and by errors in sensor data and contact models. This study combines data generation and sim-to-real transfer learning in a grasping framework that reduces the sim-to-real gap and enables precise and reliable model-free grasping. A large-scale robotic grasping dataset with dense grasp labels is generated using domain randomization methods and a novel data augmentation meth…
The University of Texas at Dallas（德克萨斯大学达拉斯分校）；St. Mark’s School of Texas（德克萨斯圣马克学校）
We introduce a neural implicit representation for grasps of objects from multiple robotic hands. Different grasps across multiple robotic hands are encoded into a shared latent space. Each latent vector is learned to decode to the 3D shape of an object and the 3D shape of a robotic hand in a grasping pose in terms of the signed distance functions of the two 3D shapes. In addition, the distance metric in the latent space is learned to preserve the similarity between grasps across different robotic hands, where the similarity of grasps is defined according to contact regions of the robotic hands…
University of Science and Technology of China（中国科学技术大学）；Lehigh University（理海大学）
High-resolution representations are important for vision-based robotic grasping problems. Existing works generally encode the input images into low-resolution representations via sub-networks and then recover high-resolution representations. This will lose spatial information, and errors introduced by the decoder will be more serious when multiple types of objects are considered or objects are far away from the camera. To address these issues, we revisit the design paradigm of CNN for robotic perception tasks. We demonstrate that using parallel branches as opposed to serial stacked convolution…
We describe a learning-based approach to hand-eye coordination for robotic grasping from monocular images. To learn hand-eye coordination for grasping, we trained a large convolutional neural network to predict the probability that task-space motion of the gripper will result in successful grasps, using only monocular camera images and independently of camera calibration or the current robot pose. This requires the network to observe the spatial relationship between the gripper and objects in the scene, thus learning hand-eye coordination. We then use this network to servo the gripper in real …
University of Warsaw（华沙大学）；IDEAS NCBR（IDEAS国家数字与区块链研究中心）；Warsaw University of Technology（华沙理工大学）；Nomagic（Nomagic公司）
Gathering real-world data from the robot quickly becomes a bottleneck when constructing a robot learning system for grasping. In this work, we design a semi-supervised grasping system that, on top of a small sample of robot experience, takes advantage of images of products to be picked, which are collected without any interactions with the robot. We validate our findings both in the simulation and in the real world. In the regime of a small number of robot training samples, taking advantage of the unlabeled data allows us to achieve performance at the level of 10-fold bigger dataset size used …
Generalising robotic grasping to previously unseen objects is a key task in general robotic manipulation. The current method for training many antipodal generative grasping models rely on a binary ground truth grasp map generated from the centre thirds of correctly labelled grasp rectangles. However, these binary maps do not accurately reflect the positions in which a robotic arm can correctly grasp a given object. We propose a continuous Gaussian representation of annotated grasps to generate ground truth training data which achieves a higher success rate on a simulated robotic grasping bench…
This paper presents an AI system applied to location and robotic grasping. Experimental setup is based on a parameter study to train a deep-learning network based on Mask-RCNN to perform waste location in indoor and outdoor environment, using five different classes and generating a new waste dataset. Initially the AI system obtain the RGBD data of the environment, followed by the detection of objects using the neural network. Later, the 3D object shape is computed using the network result and the depth channel. Finally, the shape is used to compute grasping for a robot arm with a two-finger gr…
University of South Florida（南佛罗里达大学）；National Institute of Standards and Technology (NIST)（美国国家标准与技术研究院）；German Aerospace Center (DLR)（德国航空航天中心）；Worcester Polytechnic Institute (WPI)（伍斯特理工学院）
This paper discusses recent research progress in robotic grasping and manipulation in the light of the latest Robotic Grasping and Manipulation Competitions (RGMCs). We first provide an overview of past benchmarks and competitions related to the robotics manipulation field. Then, we discuss the methodology behind designing the manipulation tasks in RGMCs. We provide a detailed analysis of key challenges for each task and identify the most difficult aspects based on the competing teams' performance in recent years. We believe that such an analysis is insightful to determine the future research …
Robotic grasping is one of the most fundamental robotic manipulation tasks and has been actively studied. However, how to quickly teach a robot to grasp a novel target object in clutter remains challenging. This paper attempts to tackle the challenge by leveraging object attributes that facilitate recognition, grasping, and quick adaptation. In this work, we introduce an end-to-end learning method of attribute-based robotic grasping with one-grasp adaptation capability. Our approach fuses the embeddings of a workspace image and a query text using a gated-attention mechanism and learns to predi…
Robotics Institute, Carnegie Mellon University（卡内基梅隆大学机器人研究所）
Precise robotic grasping is important for many industrial applications, such as assembly and palletizing, where the location of the object needs to be controlled and known. However, achieving precise grasps is challenging due to noise in sensing and control, as well as unknown object properties. We propose a method to plan robotic grasps that are both robust and precise by training two convolutional neural networks - one to predict the robustness of a grasp and another to predict a distribution of post-grasp object displacements. Our networks are trained with depth images in simulation on a da…
Data-efficient domain adaptation with only a few labelled data is desired for many robotic applications, e.g., in grasping detection, the inference skill learned from a grasping dataset is not universal enough to directly apply on various other daily/industrial applications. This paper presents an approach enabling the easy domain adaptation through a novel grasping detection network with confidence-driven semi-supervised learning, where these two components deeply interact with each other. The proposed grasping detection network specially provides a prediction uncertainty estimation mechanism…
Robotic Grasping has always been an active topic in robotics since grasping is one of the fundamental but most challenging skills of robots. It demands the coordination of robotic perception, planning, and control for robustness and intelligence. However, current solutions are still far behind humans, especially when confronting unstructured scenarios. In this paper, we survey the advances of robotic grasping, starting from the classical formulations and solutions to the modern ones. By reviewing the history of robotic grasping, we want to provide a complete view of this community, and perhaps…
6D robotic grasping beyond top-down bin-picking scenarios is a challenging task. Previous solutions based on 6D grasp synthesis with robot motion planning usually operate in an open-loop setting, which are sensitive to grasp synthesis errors. In this work, we propose a new method for learning closed-loop control policies for 6D grasping. Our policy takes a segmented point cloud of an object from an egocentric camera as input, and outputs continuous 6D control actions of the robot gripper for grasping the object. We combine imitation learning and reinforcement learning and introduce a goal-auxi…
In this paper, we investigate the problem of grasping novel objects in unstructured environments. To address this problem, consideration of the object geometry, reachability and force closure analysis are required. We propose a framework for grasping unknown objects by localizing contact regions on the contours formed by a set of depth edges in a single view 2D depth image. According to the edge geometric features obtained from analyzing the data of the depth map, the contact regions are determined. Finally,We validate the performance of the approach by applying it to the scenes with both sing…
Wearable and Assistive robotics for human grasp support are broadly either tele-operated robotic arms or act through orthotic control of a paralyzed user's hand. Such devices require correct orientation for successful and efficient grasping. In many human-robot assistive settings, the end-user is required to explicitly control the many degrees of freedom making effective or efficient control problematic. Here we are demonstrating the off-loading of low-level control of assistive robotics and active orthotics, through automatic end-effector orientation control for grasping. This paper describes…
Deep reinforcement learning (DRL) has been proven to be a powerful paradigm for learning complex control policy autonomously. Numerous recent applications of DRL in robotic grasping have successfully trained DRL robotic agents end-to-end, mapping visual inputs into control instructions directly, but the amount of training data required may hinder these applications in practice. In this paper, we propose a DRL based robotic visual grasping framework, in which visual perception and control policy are trained separately rather than end-to-end. The visual perception produces physical descriptions …
University of Waterloo（滑铁卢大学）；Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院）
There has been increasing interest in smart factories powered by robotics systems to tackle repetitive, laborious tasks. One impactful yet challenging task in robotics-powered smart factory applications is robotic grasping: using robotic arms to grasp objects autonomously in different settings. Robotic grasping requires a variety of computer vision tasks such as object detection, segmentation, grasp prediction, pick planning, etc. While significant progress has been made in leveraging of machine learning for robotic grasping, particularly with deep learning, a big challenge remains in the need…
University of Science and Technology of China（中国科学技术大学）
In this paper, we present a transformer-based architecture, namely TF-Grasp, for robotic grasp detection. The developed TF-Grasp framework has two elaborate designs making it well suitable for visual grasping tasks. The first key design is that we adopt the local window attention to capture local contextual information and detailed features of graspable objects. Then, we apply the cross window attention to model the long-term dependencies between distant pixels. Object knowledge, environmental configuration, and relationships between different visual entities are aggregated for subsequent gras…
School of CS & AI, Arizona State University（亚利桑那州立大学计算机科学与人工智能学院）
Conventional works that learn grasping affordance from demonstrations need to explicitly predict grasping configurations, such as gripper approaching angles or grasping preshapes. Classic motion planners could then sample trajectories by using such predicted configurations. In this work, our goal is instead to fill the gap between affordance discovery and affordance-based policy learning by integrating the two objectives in an end-to-end imitation learning framework based on deep neural networks. From a psychological perspective, there is a close association between attention and affordance. T…
Rochester Institute of Technology（罗切斯特理工学院）；OSARO Inc.（OSARO公司）
In this paper, we present a modular robotic system to tackle the problem of generating and performing antipodal robotic grasps for unknown objects from n-channel image of the scene. We propose a novel Generative Residual Convolutional Neural Network (GR-ConvNet) model that can generate robust antipodal grasps from n-channel input at real-time speeds (~20ms). We evaluate the proposed model architecture on standard datasets and a diverse set of household objects. We achieved state-of-the-art accuracy of 97.7% and 94.6% on Cornell and Jacquard grasping datasets respectively. We also demonstrate a…
Autonomous robotic grasping plays an important role in intelligent robotics. However, how to help the robot grasp specific objects in object stacking scenes is still an open problem, because there are two main challenges for autonomous robots: (1)it is a comprehensive task to know what and how to grasp; (2)it is hard to deal with the situations in which the target is hidden or covered by other objects. In this paper, we propose a multi-task convolutional neural network for autonomous robotic grasping, which can help the robot find the target, make the plan for grasping and finally grasp the ta…
In the robotic crop harvesting environment, foreign objects intrusion in the gripper workspace is frequently occurring and unignorable, however, rarely addressed. This paper presents a novel intelligent robotic grasping method capable of handling obstacle interference, which is the first of its kind in the literature. The proposed method combines deep learning algorithms with low-cost tactile sensing hardware on a multi-DoF soft robotic gripper. Through experimental validations, the proposed method demonstrated promising performance in distinguishing various grasping scenarios. The 4-finger in…
Google Brain（谷歌大脑）；University of California, Berkeley（加州大学伯克利分校）
In this paper, we explore deep reinforcement learning algorithms for vision-based robotic grasping. Model-free deep reinforcement learning (RL) has been successfully applied to a range of challenging environments, but the proliferation of algorithms makes it difficult to discern which particular approach would be best suited for a rich, diverse task like grasping. To answer this question, we propose a simulated benchmark for robotic grasping that emphasizes off-policy learning and generalization to unseen objects. Off-policy learning enables utilization of grasping data over a wide variety of …
6D pose recognition has been a crucial factor in the success of robotic grasping, and recent deep learning based approaches have achieved remarkable results on benchmarks. However, their generalization capabilities in real-world applications remain unclear. To overcome this gap, we introduce 6IMPOSE, a novel framework for sim-to-real data generation and 6D pose estimation. 6IMPOSE consists of four modules: First, a data generation pipeline that employs the 3D software suite Blender to create synthetic RGBD image datasets with 6D pose annotations. Second, an annotated RGBD dataset of five house…
Robotic Grasping of Harvested Tomato Trusses Using Vision and Online Learning
Delft University of Technology（代尔夫特理工大学）；Czech Technical University in Prague（布拉格捷克技术大学）；Czech Institute of Informatics, Robotics, and Cybernetics（捷克信息学、机器人学与控制论研究所）
GraspFoM: Towards Reconstruction-Driven Robotic Grasping with 3D Foundation Priors
The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；Peking University（北京大学）；The Hong Kong University of Science and Technology（香港科技大学）
Field robotic harvesting is a promising technique in recent development of agricultural industry. It is vital for robots to recognise and localise fruits before the harvesting in natural orchards. However, the workspace of harvesting robots in orchards is complex: many fruits are occluded by branches and leaves. It is important to estimate a proper grasping pose for each fruit before performing the manipulation. In this study, a geometry-aware network, A3N, is proposed to perform end-to-end instance segmentation and grasping estimation using both color and geometry sensory data from a RGB-D ca…
University of California, Merced（加州大学默塞德分校）；National Institute of Standards and Technology (NIST)（美国国家标准与技术研究院）
This technical report presents an introduction to different aspects of multi-fingered robot grasping. After having introduced relevant mathematical background for modeling, form and force closure are discussed. Next, we present an overview of various grasp planning algorithms with the objective of illustrating different approaches to solve this problem. Finally, we discuss grasp performance benchmarking.
Australian Centre for Robotic Vision（澳大利亚机器人视觉中心）；Queensland University of Technology（昆士兰科技大学）；LYRO Robotics（LYRO机器人公司）
We present the Evolved Grasping Analysis Dataset (EGAD), comprising over 2000 generated objects aimed at training and evaluating robotic visual grasp detection algorithms. The objects in EGAD are geometrically diverse, filling a space ranging from simple to complex shapes and from easy to difficult to grasp, compared to other datasets for robotic grasping, which may be limited in size or contain only a small number of object classes. Additionally, we specify a set of 49 diverse 3D-printable evaluation objects to encourage reproducible testing of robotic grasping systems across a range of compl…
This paper presents a comprehensive survey on vision-based robotic grasping. We conclude three key tasks during vision-based robotic grasping, which are object localization, object pose estimation and grasp estimation. In detail, the object localization task contains object localization without classification, object detection and object instance segmentation. This task provides the regions of the target object in the input data. The object pose estimation task mainly refers to estimating the 6D object pose and includes correspondence-based methods, template-based methods and voting-based meth…
We consider the problem of robotic grasping using depth + RGB information sampling from a real sensor. we design an encoder-decoder neural network to predict grasp policy in real time. This method can fuse the advantage of depth image and RGB image at the same time and is robust for grasp and observation height.We evaluate our method in a physical robotic system and propose an open-loop algorithm to realize robotic grasp operation. We analyze the result of experiment from multi-perspective and the result shows that our method is competitive with the state-of-the-art in grasp performance, real-…
General robotic grippers are challenging to control because of their rich nonsmooth contact dynamics and the many sources of uncertainties due to the environment or sensor noise. In this work, we demonstrate how to compute 6-DoF grasp poses using simulation-based Bayesian inference through the full stochastic forward simulation of the robot in its environment while robustly accounting for many of the uncertainties in the system. A Riemannian manifold optimization procedure preserving the nonlinearity of the rotation space is used to compute the maximum a posteriori grasp pose. Simulation and p…
In this paper, we introduce two methods of improving real-time object grasping performance from monocular colour images in an end-to-end CNN architecture. The first is the addition of an auxiliary task during model training (multi-task learning). Our multi-task CNN model improves grasping performance from a baseline average of 72.04% to 78.14% on the large Jacquard grasping dataset when performing a supplementary depth reconstruction task. The second is introducing a positional loss function that emphasises loss per pixel for secondary parameters (gripper angle and width) only on points of an …
A Hyperspectral Imaging Guided Robotic Grasping System
Department of Mechanical and Automation Engineering, T-Stone Robotics Institute, The Chinese University of Hong Kong, Hong Kong SAR（机械与自动化工程系，T-Stone机器人研究所，香港中文大学，香港特别行政区）；School of Instrumentation and Optoelectronic Engineering, Beihang University（仪器与光电工程学院，北航大学）
Many previous works approach vision-based robotic grasping by training a value network that evaluates grasp proposals. These approaches require an optimization process at run-time to infer the best action from the value network. As a result, the inference time grows exponentially as the dimension of action space increases. We propose an alternative method, by directly training a neural density model to approximate the conditional distribution of successful grasp poses from the input images. We construct a neural network that combines Gaussian mixture and normalizing flows, which is able to rep…
University of Hamburg（汉堡大学）；Knowledge Technology, Department of Informatics（知识技术与信息学系）
Combining model-based and model-free deep reinforcement learning has shown great promise for improving sample efficiency on complex control tasks while still retaining high performance. Incorporating imagination is a recent effort in this direction inspired by human mental simulation of motor behavior. We propose a learning-adaptive imagination approach which, unlike previous approaches, takes into account the reliability of the learned dynamics model used for imagining the future. Our approach learns an ensemble of disjoint local dynamics models in latent space and derives an intrinsic reward…
