Active learning of visual descriptors for grasping using non-parametric smoothed beta distributions

One of the basic skills for a robot autonomous grasping is to select the appropriate grasping point for an object. Several recent works have shown that it is possible to learn grasping points from different types of features extracted from a single image or from more complex 3D reconstructions. In the context of learning through experience, this is very convenient, since it does not require a full reconstruction of the object and implicitly incorporates kinematic constraints as the hand morphology. These learning strategies usually require a large set of labeled examples which can be expensive to obtain. In this paper, we address the problem of actively learning good grasping points to reduce the number of examples needed by the robot. The proposed algorithm computes the probability of successfully grasping an object at a given location represented by a feature vector. By autonomously exploring different feature values on different objects, the systems learn where to grasp each of the objects. The algorithm combines beta–binomial distributions and a non-parametric kernel approach to provide the full distribution for the probability of grasping. This information allows to perform an active exploration that efficiently learns good grasping points even among different objects. We tested our algorithm using a real humanoid robot that acquired the examples by experimenting directly on the objects and, therefore, it deals better with complex (anthropomorphic) hand–object interactions whose results are difficult to model, or predict. The results show a smooth generalization even in the presence of very few data as is often the case in learning through experience.     

基于多约束条件的机器人抓取策略学习方法

针对机器人在多类别物体不同任务下的抓取决策问题,提出基于多约束条件的抓取策略学习方法.该方法以抓取对象特征和抓取任务属性为机器人抓取策略约束,通过映射人类抓取习惯规划抓取模式,并采用物体方向包围盒(OBB)建立机器人抓取规则,建立多约束条件的抓取模型.利用深度径向基(DRBF)网络模型结合减聚类算法(SCM)实现抓取策略的学习,两种算法的结合旨在提高学习鲁棒性与精确性.搭建以Refiex 1型灵巧手和AUBO六自由度机械臂组成的实验平台,对多类别物体进行抓取实验.实验结果表明,所提出方法使机器人有效学习到对多物体不同任务的最优抓取策略,具有良好的抓取决策能力.     

基于机器视觉的非特定物体的智能抓取系统的研究

针对传统机械臂局限于按既定流程对固定位姿的特定物体进行机械化抓取,设计了一种基于机器视觉的非特定物体的智能抓取系统;系统通过特定的卷积神经网络对深度相机采集到的图像进行目标定位,并在图像上预测出一个该目标的可靠抓取位置,系统进一步将抓取位置信息反馈给机械臂,机械臂根据该信息完成对目标物体的抓取操作;系统基于机器人操作系统,硬件之间通过机器人操作系统的话题机制传递必要信息;最终经多次实验结果表明,通过改进的快速搜索随机树运动规划算法,桌面型机械臂能够根据神经网络模型反馈的的标记位置对不同位姿的非特定物体进行实时有效的抓取,在一定程度上提高了机械臂的自主能力,弥补了传统机械臂的不足.     

Policy search for motor primitives in robotics

Many motor skills in humanoid robotics can be learned using parametrized motor primitives. While successful applications to date have been achieved with imitation learning, most of the interesting motor learning problems are high-dimensional reinforcement learning problems. These problems are often beyond the reach of current reinforcement learning methods. In this paper, we study parametrized policy search methods and apply these to benchmark problems of motor primitive learning in robotics. We show that many well-known parametrized policy search methods can be derived from a general, common framework. This framework yields both policy gradient methods and expectation-maximization (EM) inspired algorithms. We introduce a novel EM-inspired algorithm for policy learning that is particularly well-suited for dynamical system motor primitives. We compare this algorithm, both in simulation and on a real robot, to several well-known parametrized policy search methods such as episodic REINFORCE, ??Vanilla?? Policy Gradients with optimal baselines, episodic Natural Actor Critic, and episodic Reward-Weighted Regression. We show that the proposed method out-performs them on an empirical benchmark of learning dynamical system motor primitives both in simulation and on a real robot. We apply it in the context of motor learning and show that it can learn a complex Ball-in-a-Cup task on a real Barrett WAM? robot arm.     

Active learning of inverse models with intrinsically motivated goal exploration in robots

We introduce the Self-Adaptive Goal Generation Robust Intelligent Adaptive Curiosity (SAGG-RIAC) architecture as an intrinsically motivated goal exploration mechanism which allows active learning of inverse models in high-dimensional redundant robots. This allows a robot to efficiently and actively learn distributions of parameterized motor skills/policies that solve a corresponding distribution of parameterized tasks/goals. The architecture makes the robot sample actively novel parameterized tasks in the task space, based on a measure of competence progress, each of which triggers low-level goal-directed learning of the motor policy parameters that allow to solve it. For both learning and generalization, the system leverages regression techniques which allow to infer the motor policy parameters corresponding to a given novel parameterized task, and based on the previously learnt correspondences between policy and task parameters.We present experiments with high-dimensional continuous sensorimotor spaces in three different robotic setups: (1) learning the inverse kinematics in a highly-redundant robotic arm, (2) learning omnidirectional locomotion with motor primitives in a quadruped robot, and (3) an arm learning to control a fishing rod with a flexible wire. We show that (1) exploration in the task space can be a lot faster than exploration in the actuator space for learning inverse models in redundant robots; (2) selecting goals maximizing competence progress creates developmental trajectories driving the robot to progressively focus on tasks of increasing complexity and is statistically significantly more efficient than selecting tasks randomly, as well as more efficient than different standard active motor babbling methods; (3) this architecture allows the robot to actively discover which parts of its task space it can learn to reach and which part it cannot.     

A strategy for fast grasping of unknown objects using partial shape information from range sensors

In this paper, we present a strategy for fast grasping of unknown objects based on the partial shape information from range sensors for a mobile robot with a parallel-jaw gripper. The proposed method can realize fast grasping of an unknown object without needing complete information of the object or learning from grasping experience. Information regarding the shape of the object is acquired by a 2D range sensor installed on the robot at an inclined angle to the ground. Features for determining the maximal contact area are extracted directly from the partial shape information of the unknown object to determine the candidate grasping points. Note that since the shape and mass are unknown before grasping, a successful and stable grasp cannot be in fact guaranteed. Thus, after performing a grasping trial, the mobile robot uses the 2D range sensor to judge whether the object can be lifted. If a grasping trial fails, the mobile robot will quickly find other candidate grasping points for another trial until a successful and stable grasp is realized. The proposed approach has been tested in experiments, which found that a mobile robot with a parallel-jaw gripper can successfully grasp a wide variety of objects using the proposed algorithm. The results illustrate the validity of the proposed algorithm in term of the grasping time.     

基于多尺度特征融合的抓取位姿估计

抓取目标多样性、位姿随机性严重制约了机器人抓取的任务适应性,为提高机器人抓取成功率,提出一种融合多尺度特征的机器人抓取位姿估计方法。该方法以RGD信息为输入,采用ResNet-50主干网络,融合FPN（feature pyramid networks）获得多尺度特征作为抓取生成网络的输入,以生成抓取候选框;并将抓取方向坐标映射为抓取方向的分类任务,使用ROI Align进行感兴趣区域提取,评估抓取候选框,获取目标的最优抓取位姿。为验证算法有效性,基于康奈尔抓取数据集开展了抓取位姿估计实验,仿真抓取位姿估计准确度达到96.9%。基于Inter RealSense D415深度相机和UR5机械臂搭建了实物平台,在真实场景下对位姿随机摆放的多样性目标物体进行多次抓取实验,结果显示抓取目标检测成功率为95.8%,机器人抓取成功率为90.2%。     

Few-experiential learning system of robotic picking task with selective dual-arm grasping

Recently, robots are introduced to warehouses and factories for automation and are expected to execute dual-arm manipulation as human does and to manipulate large, heavy and unbalanced objects. We focus on target picking task in the cluttered environment and aim to realize a robot picking system which the robot selects and executes proper grasping motion from single-arm and dual-arm motion. In this paper, we propose a few-experiential learning-based target picking system with selective dual-arm grasping. In our system, a robot first learns grasping points and object semantic and instance label with automatically synthesized dataset. The robot then executes and collects grasp trial experiences in the real world and retrains the grasping point prediction model with the collected trial experiences. Finally, the robot evaluates candidate pairs of grasping object instance, strategy and points and selects to execute the optimal grasping motion. In the experiments, we evaluated our system by conducting target picking task experiments with a dual-arm humanoid robot Baxter in the cluttered environment as warehouse.     

基于视觉与RFID的机器人自定位抓取算法

为实现机器人灵活的自定位,并使其准确地抓取物体,提出一种基于视觉与无线射频识别(RFID)技术的机器人自定位抓取算法。构建网格化环境,利用RFID技术确定机器人的初始位置、行进路线和方向,使用视觉系统获取物体的空间坐标,将其转换到手臂坐标系,采用改进的D-H模型对手臂进行建模,并给出机械臂逆解抓取算法。实验结果表明,该算法使得机器人定位的成功率达到76.7%,抓取成功率高达90%。     

Learning Dextrous Manipulation Skills for Multifingered Robot Hands Using the Evolution Strategy

We present a method for autonomous learning of dextrous manipulation skills with multifingered robot hands. We use heuristics derived from observations made on human hands to reduce the degrees of freedom of the task and make learning tractable. Our approach consists of learning and storing a few basic manipulation primitives for a few prototypical objects and then using an associative memory to obtain the required parameters for new objects and/or manipulations. The parameter space of the robot is searched using a modified version of the evolution strategy, which is robust to the noise normally present in real-world complex robotic tasks. Given the difficulty of modeling and simulating accurately the interactions of multiple fingers and an object, and to ensure that the learned skills are applicable in the real world, our system does not rely on simulation; all the experimentation is performed by a physical robot, in this case the 16-degree-of-freedom Utah/MIT hand. E xperimental results show that accurate dextrous manipulation skills can be learned by the robot in a short period of time. We also show the application of the learned primitives to perform an assembly task and how the primitives generalize to objects that are different from those used during the learning phase.     

Learning Dextrous Manipulation Skills for Multifingered Robot Hands Using the Evolution Strategy

We present a method for autonomous learning of dextrous manipulation skills with multifingered robot hands. We use heuristics derived from observations made on human hands to reduce the degrees of freedom of the task and make learning tractable. Our approach consists of learning and storing a few basic manipulation primitives for a few prototypical objects and then using an associative memory to obtain the required parameters for new objects and/or manipulations. The parameter space of the robot is searched using a modified version of the evolution strategy, which is robust to the noise normally present in real-world complex robotic tasks. Given the difficulty of modeling and simulating accurately the interactions of multiple fingers and an object, and to ensure that the learned skills are applicable in the real world, our system does not rely on simulation; all the experimentation is performed by a physical robot, in this case the 16-degree-of-freedom Utah/MIT hand. Experimental results show that accurate dextrous manipulation skills can be learned by the robot in a short period of time. We also show the application of the learned primitives to perform an assembly task and how the primitives generalize to objects that are different from those used during the learning phase.     

Learning how to grasp based on neural network retraining

Humans have an incredible capacity to manipulate objects using dextrous hands. A large number of studies indicate that robot learning by demonstration is a promising strategy to improve robotic manipulation and grasping performance. Concerning this subject we can ask: How does a robot learn how to grasp? This work presents a method that allows a robot to learn new grasps. The method is based on neural network retraining. With this approach we aim to enable a robot to learn new grasps through a supervisor. The proposed method can be applied for 2D and 3D cases. Extensive object databases were generated to evaluate the method performance in both 2D and 3D cases. A total of 8100 abstract shapes were generated for 2D cases and 11700 abstract shapes for 3D cases. Simulation results with a computational supervisor show that a robotic system can learn new grasps and improve its performance through the proposed HRH (Hopfield-RBF-Hopfield) grasp learning approach.     

A strategy for grasping unknown objects based on co-planarity and colour information

In this work, we describe and evaluate a grasping mechanism that does not make use of any specific object prior knowledge. The mechanism makes use of second-order relations between visually extracted multi-modal 3D features provided by an early cognitive vision system. More specifically, the algorithm is based on two relations covering geometric information in terms of a co-planarity constraint as well as appearance based information in terms of co-occurrence of colour properties. We show that our algorithm, although making use of such rather simple constraints, is able to grasp objects with a reasonable success rate in rather complex environments (i.e., cluttered scenes with multiple objects).Moreover, we have embedded the algorithm within a cognitive system that allows for autonomous exploration and learning in different contexts. First, the system is able to perform long action sequences which, although the grasping attempts not being always successful, can recover from mistakes and more importantly, is able to evaluate the success of the grasps autonomously by haptic feedback (i.e., by a force torque sensor at the wrist and proprioceptive information about the distance of the gripper after a gasping attempt). Such labelled data is then used for improving the initially hard-wired algorithm by learning. Moreover, the grasping behaviour has been used in a cognitive system to trigger higher level processes such as object learning and learning of object specific grasping.     

基于深度强化学习的固体放射性废物抓取方法研究

针对固体放射性废物分拣作业中,放射性废物杂乱无序、远程遥操作抓取效率低、人工分拣危险性大等典型问题,提出一种基于深度强化学习的放射性固体废物抓取方法。该方法使用改进深度Q网络算法,通过获取的图像信息,使机器人与环境不断进行交互并获得回报奖励,回报奖励由机械臂动作执行结果和放射性区域内放射性活度的高低构成,根据◢Q◣值的大小得到机械臂的最佳抓取位置。用V-REP软件对UR5机械臂建立仿真模型,在仿真环境中完成不同类型固体放射性废物抓取的训练与测试。仿真结果表明,固体废物在松散放置时该方法可使机械臂抓取成功率大于90%,在紧密放置时抓取成功率大于65%,机械臂不会受到废物堆叠的影响,并且会优先抓取放射性区域内具有高放射性活度的物体。