One of the first and foremost non-verbal interactions that humans perform is a handshake. It has an impact on first impressions as touch can convey complex emotions. This makes handshaking an important skill for the repertoire of a social robot. In this paper, we present a novel framework for learning reaching behaviours for human-robot handshaking behaviours for humanoid robots solely using third-person human-human interaction data. This is especially useful for non-backdrivable robots that cannot be taught by demonstrations via kinesthetic teaching. Our approach can be easily executed on different humanoid robots. This removes the need for re-training, which is especially tedious when training with human-interaction partners. We show this by applying the learnt behaviours on two different humanoid robots with similar degrees of freedom but different shapes and control limits.
Technical University of Darmstadt（达姆施塔特工业大学）；Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）
The use of social, anthropomorphic robots to support humans in various industries has been on the rise. During Human-Robot Interaction (HRI), physically interactive non-verbal behaviour is key for more natural interactions. Handshaking is one such natural interaction used commonly in many social contexts. It is one of the first non-verbal interactions which takes place and should, therefore, be part of the repertoire of a social robot. In this paper, we explore the existing state of Human-Robot Handshaking and discuss possible ways forward for such physically interactive behaviours.
Technical University of Darmstadt（达姆施塔特工业大学）；Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）
For some years now, the use of social, anthropomorphic robots in various situations has been on the rise. These are robots developed to interact with humans and are equipped with corresponding extremities. They already support human users in various industries, such as retail, gastronomy, hotels, education and healthcare. During such Human-Robot Interaction (HRI) scenarios, physical touch plays a central role in the various applications of social robots as interactive non-verbal behaviour is a key factor in making the interaction more natural. Shaking hands is a simple, natural interaction use…
Handshakes are fundamental and common greeting and parting gestures among humans. They are important in shaping first impressions as people tend to associate character traits with a person's handshake. To widen the social acceptability of robots and make a lasting first impression, a good handshaking ability is an important skill for social robots. Therefore, to test the human-likeness of a robot handshake, we propose an initial Turing-like test, primarily for the hardware interface to future AI agents. We evaluate the test on an android robot's hand to determine if it can pass for a human han…
Assistive robotic systems endeavour to support those with movement disabilities, enabling them to move again and regain functionality. Main issue with these systems is the complexity of their low-level control, and how to translate this to simpler, higher level commands that are easy and intuitive for a human user to interact with. We have created a multi-modal system, consisting of different sensing, decision making and actuating modalities, leading to intuitive, human-in-the-loop assistive robotics. The system takes its cue from the user's gaze, to decode their intentions and implement low-l…
In this paper, we aim at improving human motion prediction during human-robot collaboration in industrial facilities by exploiting contributions from both physical and physiological signals. Improved human-machine collaboration could prove useful in several areas, while it is crucial for interacting robots to understand human movement as soon as possible to avoid accidents and injuries. In this perspective, we propose a novel human-robot interface capable to anticipate the user intention while performing reaching movements on a working bench in order to plan the action of a collaborative robot…
Imperial College London（帝国理工学院）；MRC London Institute of Medical Sciences（英国医学研究理事会伦敦医学科学研究所）；Data Science Institute（数据科学研究所）
Assistive and Wearable Robotics have the potential to support humans with different types of motor impairments to become independent and fulfil their activities of daily living successfully. The success of these robot systems, however, relies on the ability to meaningfully decode human action intentions and carry them out appropriately. Neural interfaces have been explored for use in such system with several successes, however, they tend to be invasive and require training periods in the order of months. We present a robotic system for human augmentation, capable of actuating the user's arm an…
The combination of collaborative robots and end-to-end AI, promises flexible automation of human tasks in factories and warehouses. However, such promise seems a few breakthroughs away. In the meantime, humans and cobots will collaborate helping each other. For these collaborations to be effective and safe, robots need to model, predict and exploit human's intents for responsive decision making processes. Approximate Bayesian Computation (ABC) is an analysis-by-synthesis approach to perform probabilistic predictions upon uncertain quantities. ABC includes priors conveniently, leverages samplin…
Institute for AI Industry Research (AIR), Tsinghua University（清华大学人工智能产业研究院（AIR））；Computer Science and Artificial Intelligence Laboratory (CSAIL), Massachusetts Institute of Technology（麻省理工学院计算机科学与人工智能实验室（CSAIL））；School of Informatics, Xiamen University（厦门大学信息学院）
Touch is an important channel for human-robot interaction, while it is challenging for robots to recognize human touch accurately and make appropriate responses. In this paper, we design and implement a set of large-format distributed flexible pressure sensors on a robot dog to enable natural human-robot tactile interaction. Through a heuristic study, we sorted out 81 tactile gestures commonly used when humans interact with real dogs and 44 dog reactions. A gesture classification algorithm based on ResNet is proposed to recognize these 81 human gestures, and the classification accuracy reaches…
Development of a Humanoid Robot Prototype for Multimodal Human-Robot Interaction
University of Engineering and Technology, Vietnam National University, Hanoi（越南国家大学河内工程技术大学）；School of Information Science, Japan Advanced Institute of Science and Technology（日本先进科学技术学院信息科学学院）
Assistive robots enable people with disabilities to conduct everyday tasks on their own. However, these tasks can be complex, containing both coarse reaching motions and fine-grained manipulation. For example, when eating, not only does one need to move to the correct food item, but they must also precisely manipulate the food in different ways (e.g., cutting, stabbing, scooping). Shared autonomy methods make robot teleoperation safer and more precise by arbitrating user inputs with robot controls. However, these works have focused mainly on the high-level task of reaching a goal from a discre…
Istituto Italiano di Tecnologia（意大利理工学院）；Czech Technical University in Prague（布拉格捷克理工大学）；Yale University（耶鲁大学）
With robots leaving factories and entering less controlled domains, possibly sharing the space with humans, safety is paramount and multimodal awareness of the body surface and the surrounding environment is fundamental. Taking inspiration from peripersonal space representations in humans, we present a framework on a humanoid robot that dynamically maintains such a protective safety zone, composed of the following main components: (i) a human 2D keypoints estimation pipeline employing a deep learning based algorithm, extended here into 3D using disparity; (ii) a distributed peripersonal space …
In this paper we present a neurally plausible model of robot reaching inspired by human infant reaching that is based on embodied artificial intelligence, which emphasizes the importance of the sensory-motor interaction of an agent and the world. This model encompasses both learning sensory-motor correlations through motor babbling and also arm motion planning using spreading activation. This model is organized in three layers of neural maps with parallel structures representing the same sensory-motor space. The motor babbling period shapes the structure of the three neural maps as well as the…
Monash University（莫纳什大学）；University of British Columbia（不列颠哥伦比亚大学）
The Minimum Jerk motion model has long been cited in literature for human point-to-point reaching motions in single-person tasks. While it has been demonstrated that applying minimum-jerk-like trajectories to robot reaching motions in the joint action task of human-robot handovers allows a robot giver to be perceived as more careful, safe, and skilled, it has not been verified whether human reaching motions in handovers follow the Minimum Jerk model. To experimentally test and verify motion models for human reaches in handovers, we examined human reaching motions in unconstrained handovers (wh…
Plant-inspired behavior-based controller to enable reaching in redundant continuum robot arms
The BioRobotics Institute, Sant’Anna School of Advanced Studies（圣安娜高等研究院生物机器人研究所）；Department of Mechanical Engineering, National University of Singapore（新加坡国立大学机械工程系）
Aristotle University of Thessaloniki（塞萨洛尼基亚里士多德大学）
In this work, a control scheme for approaching and unveiling a partially occluded object of interest is proposed.The control scheme is based only on the classified point cloud obtained by the in-hand camera attached to the robot's end effector. It is shown that the proposed controller reaches in the vicinity of the object progressively unveiling the neighborhood of each visible point of the object of interest. It can therefore potentially achieve the complete unveiling of the object. The proposed control scheme is evaluated through simulations and experiments with a UR5e robot with an in-hand …
University of Pennsylvania（宾夕法尼亚大学）；GRASP Lab（GRASP实验室）；Department of Electrical and Systems Engineering, University of Pennsylvania（宾夕法尼亚大学电气与系统工程系）
In this paper, we propose a novel architecture and a self-supervised policy gradient algorithm, which employs unsupervised auxiliary tasks to enable a mobile robot to learn how to navigate to a given goal. The dependency on the global information is eliminated by providing only sparse range-finder measurements to the robot. The partially observable planning problem is addressed by splitting it into a hierarchical process. We use convolutional networks to plan locally, and a differentiable memory to provide information about past time steps in the trajectory. These modules, combined in our netw…
Robot navigation in human semi-static and crowded environments can lead to the freezing problem, where the robot can not move due to the presence of humans standing on its path and no other path is available. Classical approaches of robot navigation do not provide a solution for this problem. In such situations, the robot could interact with the humans in order to clear its path instead of considering them as unanimated obstacles. In this work, we propose a robot behavior for a wheeled humanoid robot that complains with social norms for clearing its path when the robot is frozen due to the pre…
Planning balanced and collision-free motion for humanoid robots is non-trivial, especially when they are operated in complex environments, such as reaching targets behind obstacles or through narrow passages. We propose a method that allows us to apply existing sampling--based algorithms to plan trajectories for humanoids by utilizing a customized state space representation, biased sampling strategies, and a steering function based on a robust inverse kinematics solver. Our approach requires no prior offline computation, thus one can easily transfer the work to new robot platforms. We tested t…
Applied AI Lab (A2I)（应用人工智能实验室）；Dynamic Robot Systems (DRS)（动态机器人系统实验室）；Oxford Robotics Institute (ORI), University of Oxford（牛津大学牛津机器人研究所）
We present a novel approach to path planning for robotic manipulators, in which paths are produced via iterative optimisation in the latent space of a generative model of robot poses. Constraints are incorporated through the use of constraint satisfaction classifiers operating on the same space. Optimisation leverages gradients through our learned models that provide a simple way to combine goal reaching objectives with constraint satisfaction, even in the presence of otherwise non-differentiable constraints. Our models are trained in a task-agnostic manner on randomly sampled robot poses. In …
University of Leeds（利兹大学）；School of Computing, University of Leeds（利兹大学计算机学院）；School of Psychology, University of Leeds（利兹大学心理学院）；Centre for Immersive Technologies, University of Leeds（利兹大学沉浸式技术中心）
Humans, in comparison to robots, are remarkably adept at reaching for objects in cluttered environments. The best existing robot planners are based on random sampling of configuration space -- which becomes excessively high-dimensional with large number of objects. Consequently, most planners often fail to efficiently find object manipulation plans in such environments. We addressed this problem by identifying high-level manipulation plans in humans, and transferring these skills to robot planners. We used virtual reality to capture human participants reaching for a target object on a tabletop…
Self-navigation, referred as the capability of automatically reaching the goal while avoiding collisions with obstacles, is a fundamental skill required for mobile robots. Recently, deep reinforcement learning (DRL) has shown great potential in the development of robot navigation algorithms. However, it is still difficult to train the robot to learn goal-reaching and obstacle-avoidance skills simultaneously. On the other hand, although many DRL-based obstacle-avoidance algorithms are proposed, few of them are reused for more complex navigation tasks. In this paper, a novel danger-aware adaptiv…
Cornell University（康奈尔大学）；The University of Texas at Austin（德克萨斯大学奥斯汀分校）；University of Washington（华盛顿大学）
We present our runner-up approach for the Real Robot Challenge 2021. We build upon our previous approach used in Real Robot Challenge 2020. To solve the task of sequential goal-reaching we focus on two aspects to achieving near-optimal trajectory: Grasp stability and Controller performance. In the RRC 2021 simulated challenge, our method relied on a hand-designed Pinch grasp combined with Trajectory Interpolation for better stability during the motion for fast goal-reaching. In Stage 1, we observe reverting to a Triangular grasp to provide a more stable grasp when combined with Trajectory Inte…
The control of a robot for manipulation tasks generally relies on object detection and pose estimation. An attractive alternative is to learn control policies directly from raw input data. However, this approach is time-consuming and expensive since learning the policy requires many trials with robot actions in the physical environment. To reduce the training cost, the policy can be learned in simulation with a large set of synthetic images. The limit of this approach is the domain gap between the simulation and the robot workspace. In this paper, we propose to learn a policy for robot reachin…
In many human-in-the-loop robotic applications such as robot-assisted surgery and remote teleoperation, predicting the intended motion of the human operator may be useful for successful implementation of shared control, guidance virtual fixtures, and predictive control. Developing computational models of human movements is a critical foundation for such motion prediction frameworks. With this motivation, we present a computational framework for modeling reaching movements in the presence of obstacles. We propose a stochastic optimal control framework that consists of probabilistic collision av…
Reaching tasks with random targets and obstacles is a challenging task for robotic manipulators. In this study, we propose a novel model-free reinforcement learning approach based on proximal policy optimization (PPO) for training a deep policy to map the task space to the joint space of a 6-DoF manipulator. To facilitate the training process in a large workspace, we develop an efficient representation of environmental inputs and outputs. The calculation of the distance between obstacles and manipulator links is incorporated into the state representation using a geometry-based method. Addition…
KIST（韩国科学技术研究院）；Georgia Institute of Technology（佐治亚理工学院）
This technical report gives an overview of our work on control algorithms dealing with redundant robot systems for achieving human-like motion characteristics. Previously, we developed a novel control law to exhibit human-motion characteristics in redundant robot arm systems as well as arm-trunk systems for reaching tasks [1], [2]. This newly developed method nullifies the need for the computation of pseudo-inverse of Jacobian while the formulation and optimization of any artificial performance index is not necessary. The time-varying properties of the muscle stiffness and damping as well as t…
Robots should understand both semantics and physics to be functional in the real world. While robot platforms provide means for interacting with the physical world they cannot autonomously acquire object-level semantics without needing human. In this paper, we investigate how to minimize human effort and intervention to teach robots perform real world tasks that incorporate semantics. We study this question in the context of visual servoing of mobile robots and propose DIViS, a Domain Invariant policy learning approach for collision free Visual Servoing. DIViS incorporates high level semantics…
Max-Planck-Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）；Worcester Polytechnic Institute（伍斯特理工学院）
To enable safe and efficient human-robot collaboration in shared workspaces it is important for the robot to predict how a human will move when performing a task. While predicting human motion for tasks not known a priori is very challenging, we argue that single-arm reaching motions for known tasks in collaborative settings (which are especially relevant for manufacturing) are indeed predictable. Two hypotheses underlie our approach for predicting such motions: First, that the trajectory the human performs is optimal with respect to an unknown cost function, and second, that human adaptation …
Reinforcement learning has shown great promise in the training of robot behavior due to the sequential decision making characteristics. However, the required enormous amount of interactive and informative training data provides the major stumbling block for progress. In this study, we focus on accelerating reinforcement learning (RL) training and improving the performance of multi-goal reaching tasks. Specifically, we propose a precision-based continuous curriculum learning (PCCL) method in which the requirements are gradually adjusted during the training process, instead of fixing the paramet…
The ability to adapt to uncertainties, recover from failures, and coordinate between hand and fingers are essential sensorimotor skills for fully autonomous robotic grasping. In this paper, we aim to study a unified feedback control policy for generating the finger actions and the motion of hand to accomplish seamlessly coordinated tasks of reaching, grasping and re-grasping. We proposed a set of quantified metrics for task-orientated rewards to guide the policy exploration, and we analyzed and demonstrated the effectiveness of each reward term. To acquire a robust re-grasping motion, we deplo…
Czech Technical University in Prague（布拉格捷克理工大学）；Oxford Brookes University（牛津布鲁克斯大学）
The mechanisms of infant development are far from understood. Learning about one's own body is likely a foundation for subsequent development. Here we look specifically at the problem of how spontaneous touches to the body in early infancy may give rise to first body models and bootstrap further development such as reaching competence. Unlike visually elicited reaching, reaching to own body requires connections of the tactile and motor space only, bypassing vision. Still, the problems of high dimensionality and redundancy of the motor system persist. In this work, we present an embodied comput…
Humanoid robotics is a promising field because the strong human preference to interact with anthropomorphic interfaces. Despite this, humanoid robots are far from reaching main stream adoption and the features available in such robots seem to lag that of the latest smartphones. A fragmented robot ecosystem and low incentives to developers do not help to foster the creation of Robot-Apps either. In contrast, smartphones enjoy high adoption rates and a vibrant app ecosystem (4M apps published). Given this, it seems logical to apply the mobile SW and HW development model to humanoid robots. One w…
ARC Centre of Excellence for Robotic Vision (ACRV)（ARC机器人视觉卓越中心（ACRV））；Queensland University of Technology (QUT)（昆士兰科技大学（QUT））
This paper introduces a machine learning based system for controlling a robotic manipulator with visual perception only. The capability to autonomously learn robot controllers solely from raw-pixel images and without any prior knowledge of configuration is shown for the first time. We build upon the success of recent deep reinforcement learning and develop a system for learning target reaching with a three-joint robot manipulator using external visual observation. A Deep Q Network (DQN) was demonstrated to perform target reaching after training in simulation. Transferring the network to real h…
Achieving short-distance flight helps improve the efficiency of humanoid robots moving in complex environments (e.g., crossing large obstacles or reaching high places) for rapid emergency missions. This study proposes a design of a flying humanoid robot named Jet-HR2. The robot has 10 joints driven by brushless motors and harmonic drives for locomotion. To overcome the challenge of the stable-attitude takeoff in small thrust-to-weight conditions, the robot was designed based on the concept of thrust vectoring. The propulsion system consists of four ducted fans, that is, two fixed on the waist …
Dual-Agent Multiple-Model Reinforcement Learning for Event-Triggered Human-Robot Co-Adaptation in Decoupled Task Spaces
College of Medical information（医学信息学院）；Artificial intelligence, Shandong First Medical University (Shandong Academy of Medical Science) 6699 Qingdao Road, Jinan, Shandong, China（人工智能，山东第一医科大学（山东医学科学院）6699青岛路，济南，山东，中国）；Faculty of Engineering（工程学院）；IT, University of Technology Sydney, Australia（信息技术，悉尼科技大学，澳大利亚）
