关键词： Learning and adaptive systems   Bayesian non-parametrics   online learning   hidden semi-Markov model   subspace clustering   teleoperation  

摘要： Small-variance asymptotics is emerging as a useful technique for inference in large-scale Bayesian non-parametric mixture models. This paper analyzes the online learning of robot manipulation tasks with Bayesian non-parametric mixture models under small-variance asymptotics. The analysis yields a scalable online sequence clustering (SOSC) algorithm that is non-parametric in the number of clusters and the subspace dimension of each cluster. SOSC groups the new datapoint in low-dimensional subspaces by online inference in a non-parametric mixture of probabilistic principal component analyzers (MPPCA) based on a Dirichlet process, and captures the state transition and state duration information online in a hidden semi-Markov model (HSMM) based on a hierarchical Dirichlet process. A task-parameterized formulation of our approach autonomously adapts the model to changing environmental situations during manipulation. We apply the algorithm in a teleoperation setting to recognize the intention of the operator and remotely adjust the movement of the robot using the learned model. The generative model is used to synthesize both time-independent and time-dependent behaviors by relying on the principles of shared and autonomous control. Experiments with the Baxter robot yield parsimonious clusters that adapt online with new demonstrations and assist the operator in performing remote manipulation tasks.

关键词： aerial gripping   flying robots   high-speed landing   MBZIRC   multiagent aerial system  

摘要： This study describes the hardware and software systems of the Micro Aerial Vehicle (MAV) platforms used by the ETH Zurich team in the 2017 Mohamed Bin Zayed International Robotics Challenge (MBZIRC). The aim was to develop robust outdoor platforms with the autonomous capabilities required for the competition, by applying and integrating knowledge from various fields, including computer vision, sensor fusion, optimal control, and probabilistic robotics. This paper presents the major components and structures of the system architectures and reports on experimental findings for the MAV-based challenges in the competition. Main highlights include securing the second place both in the individual search, pick, and place the task of Challenge 3 and the Grand Challenge, with autonomous landing executed in less than 1 min and a visual servoing success rate of over 90% for object pickups.

关键词： Helical swimmer robot   Single helical flagellum   Hydrodynamics maneuver   Flagellum inclination angle  

摘要： Helical swimming robots with a capable propulsion system at low-Reynolds numbers have been proposed for many applications. Although linear propulsion characteristics of swimming robots with a single helical flagellum have been extensively studied, the characteristics of maneuverability have not been completely investigated yet. This study presents a new method for the maneuverability of the helical swimming robot with a single helical flagellum. This mechanism is based on the change in the angle between the helical and body axes. This study shows that a change in the aforementioned angle can enable the swimming robot to have turning maneuvers in clockwise or counterclockwise directions. Moreover, the swimming robot will move in a straight line if the helical and body axes are parallel. To investigate this new method and predict the robot's behavior at various inclination angles, a hydrodynamics model is used. To validate the hydrodynamics model, an experimental prototype of a macro-size swimming robot with specific inclination angles is fabricated. The results indicate that the helical swimming robot swims on circular trajectories through specific inclination angles between the helical flagellum and the body axis. Moreover, the radius of curvature decreases by increasing the inclination angle. Results of the validated hydrodynamics model indicate that the turning velocity has approximately a constant value at different inclination angles depending on the rotational frequency and geometrical parameters of the swimming robot. Finally, the effects of geometrical parameters of the body and the helical flagellum on the radius of curvature and turning velocity are investigated through the proposed hydrodynamics model. The verified results indicate that the hydrodynamics model provides a viable alternative model to predict the behavior of a helical swimming robot at various inclination angles within a range of design variables. This new method can be introduced as a mechan

关键词： Automated planning   Planning and execution   Anytime framework   Autonomous robots  

摘要： Acting in robotics is driven by reactive and deliberative reasonings which take place in the competition between execution and planning processes. Properly balancing reactivity and deliberation is still an open question for harmonious execution of deliberative plans in complex robotic applications. We propose a flexible algorithmic framework to allow continuous real-time planning of complex tasks in parallel of their executions. Our framework, named AMPLE, is oriented towards robotic modular architectures in the sense that it turns planning algorithms into services that must be generic, reactive, and valuable. Services are optimized actions that are delivered at precise time points following requests from other modules that include states and dates at which actions are needed. To this end, our framework is divided in two concurrent processes: a planning thread which receives planning requests and delegates action selection to embedded planning softwares in compliance with the queue of internal requests, and an execution thread which orchestrates these planning requests as well as action execution and state monitoring. We show how the behavior of the execution thread can be parametrized to achieve various strategies which can differ, for instance, depending on the distribution of internal planning requests over possible future execution states in anticipation of the uncertain evolution of the system, or over different underlying planners to take several levels into account. We demonstrate the flexibility and the relevance of our framework on various robotic benchmarks and real experiments that involve complex planning problems of different natures which could not be properly tackled by existing dedicated planning approaches which rely on the standard plan-then-execute loop.

关键词： Robots   Sliding Mode Control   Poisson's Ratio   Contact Dynamics   Satellites   Space Debris   Damping Coefficient   Numerical Simulation   Space Environment   Nonlinear Systems  

摘要： The whole capture process of the tethered space net robot (TSNR) is investigated in a study and the criterion of a successful net capture is discussed. If the behavior of the net after collision does not satisfy the criterion, which means that the net may not totally wrap around the target, a net closing control algorithm is needed to ensure a successful capture. The net closing of the TSNR after collision is also focused upon in this study. The mass-spring model of the TSNR and the continuous contact dynamic model are derived for the investigations. To investigate the contact dynamics of the TSNR, four critical capture parameters are identified and analyzed based on numerical simulations. The criterion to describe a successful net capture is also discussed.

关键词： Accelerator   autonomous robot   edge computing   low power   reinforcement learning (RL)   stochastic synapse  

摘要： Reinforcement learning (RL) is a bio-mimetic learning approach, where agents can learn about an environment by performing specific tasks without any human supervision. RL is inspired by behavioral psychology, where agents take actions to maximize a cumulative reward. In this paper, we present an RL neuromorphic accelerator capable of performing obstacle avoidance in a mobile robot at the edge of the cloud. We propose an energy-efficient time-domain mixed-signal (TD-MS) computational framework. In TD-MS computation, we demonstrate that the energy to compute is proportional to the importance of the computation. We leverage the unique properties of stochastic networks and recent advances in Q-learning in the proposed RL implementation. The 55-nm test chip implements RL using a three-layered fully connected neural network and consumes a peak power of 690 mu W.

关键词： Artificial Intelligence   Automation   Future of Humanity   Robotics  

摘要： The exponential advancement in artificial intelligence (AI), machine learning, robotics, and automation are rapidly transforming industries and societies across the world. The way we work, the way we live, and the way we interact with others are expected to be transformed at a speed and scale beyond anything we have observed in human history. This new industrial revolution is expected, on one hand, to enhance and improve our lives and societies. On the other hand, it has the potential to cause major upheavals in our way of life and our societal norms. The window of opportunity to understand the impact of these technologies and to preempt their negative effects is closing rapidly. Humanity needs to be proactive, rather than reactive, in managing this new industrial revolution. This article looks at the promises, challenges, and future research directions of these transformative technologies. Not only are the technological aspects investigated, but behavioral, societal, policy, and governance issues are reviewed as well. This research contributes to the ongoing discussions and debates about AI, automation, machine learning, and robotics. It is hoped that this article will heighten awareness of the importance of understanding these disruptive technologies as a basis for formulating policies and regulations that can maximize the benefits of these advancements for humanity and, at the same time, curtail potential dangers and negative impacts.

关键词： Automation systems   dynamic software systems   reconfigurable and interoperable systems   service robotics   service-oriented architecture (SOA)  

摘要： The heterogeneity of execution platforms and operating software in manufacturing machines and robots, as well as various sensors and actuators, creates challenges for integration into larger systems. Existing approaches make use of different types of middleware to mitigate the challenges of designing interoperable systems. However, middleware can significantly impede modular design and composition of software systems that are dynamic in nature. This paper elaborates upon those challenges and proposes using an approach called service-oriented SystemJ (SOSJ), based on the system-level programming language SystemJ enhanced with service oriented features. This approach allows developers to design dynamic software systems while adopting and incorporating legacy solutions. The approach is demonstrated on the integration of an industrial automation system, incorporating the use of multiple modular mechatronics stations and service robotics systems, represented by robot operating system-enabled Baxter robots. The proposed approach offers a simple service interface based on abstract objects for integrating robots and automation machines in the SOSJ world, without the need to modify the underlying mechatronics or robotics systems.

关键词： Special issues and sections   Manufacturing industries   Manufacturing processes   Industries   Technology forecasting   Robots   Robotic assembly  

摘要： The papers in this special section examine robotic technologies of the fourth industrial revolution or Industry 4.0 that will impact manufacturing industries. The concept of the fourth industrial revolution has drawn attention throughout the world and many efforts to define the concept in diverse fields have continued. Generally, the concept can be summarized as the technology convergence through hyper-intelligence and hyper-connectivity. The core technologies providing the thrust of the fourth industrial revolution, especially in the industrial informatics field, are Internet of Things, robotics, virtual reality, and artificial intelligence. As one of the most critical characteristics of the fourth industrial revolution technology is that the boundary between cyber space and physical space becomes unclear, innovations in industry and business initiate through the fusion of these two spaces. It is the robotic system that plays the key role as a physical medium linking cyber and physical spaces and even changing the physical space through direct interactions. In this sense, robotic system should be recognized as a crucial platform in performing tasks in the cyber-physical space.