We present a robotic system for picking a target from a pile of objects that is capable of finding and grasping the target object by removing obstacles in the appropriate order. The fundamental idea is to segment instances with both visible and occluded masks, which we call `instance occlusion segmentation'. To achieve this, we extend an existing instance segmentation model with a novel `relook' architecture, in which the model explicitly learns the inter-instance relationship. Also, by using image synthesis, we make the system capable of handling new objects without human annotations. The experimental results show the effectiveness of the relook architecture when compared with a conventional model and of the image synthesis when compared to a human-annotated dataset. We also demonstrate the capability of our system to achieve picking a target in a cluttered environment with a real robot.
Instance segmentation is an important pre-processing task in numerous real-world applications, such as robotics, autonomous vehicles, and human-computer interaction. Compared with the rapid development of deep learning for two-dimensional (2D) image tasks, deep learning-based instance segmentation of 3D point cloud still has a lot of room for development. In particular, distinguishing a large number of occluded objects of the same class is a highly challenging problem, which is seen in a robotic bin-picking. In a usual bin-picking scene, many identical objects are stacked together and the mode…
Modern object detection and instance segmentation networks stumble when picking out humans in crowded or highly occluded scenes. Yet, these are often scenarios where we require our detectors to work well. Many works have approached this problem with model-centric improvements. While they have been shown to work to some extent, these supervised methods still need sufficient relevant examples (i.e. occluded humans) during training for the improvements to be maximised. In our work, we propose a simple yet effective data-centric approach, Occlusion Copy & Paste, to introduce occluded examples to m…
Gwangju Institute of Science and Technology（光州科学技术院）
Instance-aware segmentation of unseen objects is essential for a robotic system in an unstructured environment. Although previous works achieved encouraging results, they were limited to segmenting the only visible regions of unseen objects. For robotic manipulation in a cluttered scene, amodal perception is required to handle the occluded objects behind others. This paper addresses Unseen Object Amodal Instance Segmentation (UOAIS) to detect 1) visible masks, 2) amodal masks, and 3) occlusions on unseen object instances. For this, we propose a Hierarchical Occlusion Modeling (HOM) scheme desi…
Objects grasping, also known as the bin-picking, is one of the most common tasks faced by industrial robots. While much work has been done in related topics, grasping randomly piled objects still remains a challenge because much of the existing work either lack robustness or costs too much resource. In this paper, we develop a fast and robust bin-picking system for grasping densely piled objects adaptively and safely. The proposed system starts with point cloud segmentation using improved density-based spatial clustering of application with noise (DBSCAN) algorithm, which is improved by combin…
Khalifa University（哈利法大学）；Durham University（杜伦大学）；COSMONiO AI；The University of Western Australia（西澳大学）；Inception Institute of Artificial Intelligence（人工智能研究院）
In the last two decades, baggage scanning has globally become one of the prime aviation security concerns. Manual screening of the baggage items is tedious, error-prone, and compromise privacy. Hence, many researchers have developed X-ray imagery-based autonomous systems to address these shortcomings. This paper presents a cascaded structure tensor framework that can automatically extract and recognize suspicious items in heavily occluded and cluttered baggage. The proposed framework is unique, as it intelligently extracts each object by iteratively picking contour-based transitional informati…
University of Bonn（波恩大学）；University of Adelaide（阿德莱德大学）
Autonomous robotic manipulation in clutter is challenging. A large variety of objects must be perceived in complex scenes, where they are partially occluded and embedded among many distractors, often in restricted spaces. To tackle these challenges, we developed a deep-learning approach that combines object detection and semantic segmentation. The manipulation scenes are captured with RGB-D cameras, for which we developed a depth fusion method. Employing pretrained features makes learning from small annotated robotic data sets possible. We evaluate our approach on two challenging data sets: on…
The picking of one or more objects from an unsorted pile continues to be non-trivial for robotic systems. This is especially so when the pile consists of a granular material (GM) containing individual items that tangle with one another, causing more to be picked out than desired. One of the key features of such tangle-prone GMs is the presence of protrusions extending out from the main body of items in the pile. This work characterises the role the latter play in causing mechanical entanglement and their impact on picking consistency. It reports experiments in which picking GMs with different …
We present joint learning of instance and semantic segmentation for visible and occluded region masks. Sharing the feature extractor with instance occlusion segmentation, we introduce semantic occlusion segmentation into the instance segmentation model. This joint learning fuses the instance- and image-level reasoning of the mask prediction on the different segmentation tasks, which was missing in the previous work of learning instance segmentation only (instance-only). In the experiments, we evaluated the proposed joint learning comparing the instance-only learning on the test dataset. We als…
In bin-picking scenarios, multiple instances of an object of interest are stacked in a pile randomly, and hence, the instances are inherently subjected to the challenges: severe occlusion, clutter, and similar-looking distractors. Most existing methods are, however, for single isolated object instances, while some recent methods tackle crowd scenarios as post-refinement which accounts multiple object relations. In this paper, we address recovering 6D poses of multiple instances in bin-picking scenarios in depth modality by multi-task learning in deep neural networks. Our architecture jointly l…
Graduate School of Engineering Science, Osaka University（大阪大学工程科学研究生院）；Intelligent Systems Research Institute, National Institute of Advanced Industrial Science and Technology（日本产业技术综合研究所智能系统研究所）
In this research, we tackle the problem of picking an object from randomly stacked pile. Since complex physical phenomena of contact among objects and fingers makes it difficult to perform the bin-picking with high success rate, we consider introducing a learning based approach. For the purpose of collecting enough number of training data within a reasonable period of time, we introduce a physics simulator where approximation is used for collision checking. In this paper, we first formulate the learning based robotic bin-picking by using CNN (Convolutional Neural Network). We also obtain the o…
Osaka University（大阪大学）；National Institute of Advanced Industrial Science and Technology (AIST)（产业技术综合研究所（AIST））；Kanazawa University（金泽大学）；Toyota Motors Co., Ltd.（丰田汽车公司）
This paper shows experimental results on learning based randomized bin-picking combined with iterative visual recognition. We use the random forest to predict whether or not a robot will successfully pick an object for given depth images of the pile taking the collision between a finger and a neighboring object into account. For the discriminator to be accurate, we consider estimating objects' poses by merging multiple depth images of the pile captured from different points of view by using a depth sensor attached at the wrist. We show that, even if a robot is predicted to fail in picking an o…
Robots working in human environments must be able to perceive and act on challenging objects with articulations, such as a pile of tools. Articulated objects increase the dimensionality of the pose estimation problem, and partial observations under clutter create additional challenges. To address this problem, we present a generative-discriminative parts-based recognition and localization method for articulated objects in clutter. We formulate the problem of articulated object pose estimation as a Markov Random Field (MRF). Hidden nodes in this MRF express the pose of the object parts, and edg…
We present a research picking prototype related to our company's industrial waste sorting application. The goal of the prototype is to be as autonomous as possible and it both calibrates itself and improves its picking with minimal human intervention. The system learns to pick objects better based on a feedback sensor in its gripper and uses machine learning to choosing the best proposal from a random sample produced by simple hard-coded geometric models. We show experimentally the system improving its picking autonomously by measuring the pick success rate as function of time. We also show ho…
National Inst. of Advanced Industrial Science and Technology（产业技术综合研究所）；Osaka Univ.（大阪大学）；Kanazawa Univ.（金泽大学）；Toyota Motors Co. Ltd.（丰田汽车公司）
This paper proposes a iterative visual recognition system for learning based randomized bin-picking. Since the configuration on randomly stacked objects while executing the current picking trial is just partially different from the configuration while executing the previous picking trial, we consider detecting the poses of objects just by using a part of visual image taken at the current picking trial where it is different from the visual image taken at the previous picking trial. By using this method, we do not need to try to detect the poses of all objects included in the pile at every picki…
Osaka University（大阪大学）；National Institute of Advanced Industrial Science and Technology (AIST)（产业技术综合研究所）；Kanazawa University（金泽大学）；Toyota Motors Co., Ltd.（丰田汽车公司）
This paper proposes a novel method for randomized bin-picking based on learning. When a two-fingered gripper tries to pick an object from the pile, a finger often contacts a neighboring object. Even if a finger contacts a neighboring object, the target object will be successfully picked depending on the configuration of neighboring objects. In our proposed method, we use the visual information on neighboring objects to train the discriminator. Corresponding to a grasping posture of an object, the discriminator predicts whether or not the pick will be successful even if a finger contacts a neig…
In this letter, we present an interactive probabilistic mapping framework for a mobile manipulator picking objects from a pile. The aim is to map the scene, actively decide where to go next and which object to pick, make changes to the scene by picking the chosen object, and then map these changes alongside. The proposed framework uses a novel dynamic Gaussian Process (GP) Implicit Surface method to incrementally build and update the scene map that reflects environment changes. Actively the framework provides the next-best-view, balancing the need for picking object reachability with map infor…
Dyson Robotics Laboratory（戴森机器人实验室）；Imperial College London（伦敦帝国理工学院）
Robots need object-level scene understanding to manipulate objects while reasoning about contact, support, and occlusion among objects. Given a pile of objects, object recognition and reconstruction can identify the boundary of object instances, giving important cues as to how the objects form and support the pile. In this work, we present a system, SafePicking, that integrates object-level mapping and learning-based motion planning to generate a motion that safely extracts occluded target objects from a pile. Planning is done by learning a deep Q-network that receives observations of predicte…
ETH Zurich（苏黎世联邦理工学院）；ABB Corporate Research（ABB集团企业研究中心）
Picking a specific object from clutter is an essential component of many manipulation tasks. Partial observations often require the robot to collect additional views of the scene before attempting a grasp. This paper proposes a closed-loop next-best-view planner that drives exploration based on occluded object parts. By continuously predicting grasps from an up-to-date scene reconstruction, our policy can decide online to finalize a grasp execution or to adapt the robot's trajectory for further exploration. We show that our reactive approach decreases execution times without loss of grasp succ…
This work proposes a robot task planning framework for retrieving a target object in a confined workspace among multiple stacked objects that obstruct the target. The robot can use prehensile picking and in-workspace placing actions. The method assumes access to 3D models for the visible objects in the scene. The key contribution is in achieving desirable properties, i.e., to provide (a) safety, by avoiding collisions with sensed obstacles, objects, and occluded regions, and (b) resolution completeness (RC) - or probabilistic completeness (PC) depending on implementation - which indicates a so…
Many order fulfillment applications in logistics, such as packing, involve picking objects from unstructured piles before tightly arranging them in bins or shipping containers. Desirable robotic solutions in this space need to be low-cost, robust, easily deployable and simple to control. The current work proposes a complete pipeline for solving packing tasks for cuboid objects, given access only to RGB-D data and a single robot arm with a vacuum-based end-effector, which is also used as a pushing or dragging finger. The pipeline integrates perception for detecting the objects and planning so a…
