Positive affect has been linked to increased interest, curiosity and satisfaction in human learning. In reinforcement learning, extrinsic rewards are often sparse and difficult to define, intrinsically motivated learn...
详细信息
ISBN:
(纸本)9781728190778
Positive affect has been linked to increased interest, curiosity and satisfaction in human learning. In reinforcement learning, extrinsic rewards are often sparse and difficult to define, intrinsically motivated learning can help address these challenges. We argue that positive affect is an important intrinsic reward that effectively helps drive exploration that is useful in gathering experiences. We present a novel approach leveraging a task-independent reward function trained on spontaneous smile behavior that reflects the intrinsic reward of positive affect. To evaluate our approach we trained several downstream computer vision tasks on data collected with our policy and several baseline methods. We show that the policy based on our affective rewards successfully increases the duration of episodes, the area explored and reduces collisions. The impact is the increased speed of learning for several downstream computer vision tasks.
Motivated by the limited flight time of battery-powered multi-rotor UAVs, in this paper we address the problem of generating energy-optimal trajectories for a planar quadrotor. More specifically, by considering an acc...
详细信息
ISBN:
(纸本)9781728190778
Motivated by the limited flight time of battery-powered multi-rotor UAVs, in this paper we address the problem of generating energy-optimal trajectories for a planar quadrotor. More specifically, by considering an accurate electrical model for the brushless DC motors and rest-to-rest maneuvers between two predefined boundary states, we explicitly compute the minimum-energy curves by adopting a free and a fixed end-time optimal control formulation. The numerical solution of these optimal control problems hinges upon a simple yet effective indirect projected gradient method. Simulation experiments illustrate the theory in a variety of realistic flight scenarios.
Summary form only given. ABB has launched its fifth generation robot controller, the IRC5. The basic motion control of the IRC5 controller includes the TrueMove and QuickMove functionality for best possible production...
详细信息
Summary form only given. ABB has launched its fifth generation robot controller, the IRC5. The basic motion control of the IRC5 controller includes the TrueMove and QuickMove functionality for best possible production rate and quality. In addition to this, the MultiMove function enables new production concepts and more cost-effective solutions. To penetrate new market segments, ease-of-use, high precision and cost-effectiveness are important factors. The availability of low-cost computational power and, in some cases, sensor integration enables the use of cost-effective industrial robots for high-precision tasks.
To get sufficient environmental information for a teleoperated unmanned vehicle, a matched image with wide field and high quality image is necessary. Image matching is a key point in image mosaic. And the vast amounts...
详细信息
Parallel mechanisms are becoming increasingly popular as subsystems in various robots due to their superior stiffness, payload-to-weight ratio, and dynamic properties. The serial connection of parallel subsystems lead...
详细信息
ISBN:
(纸本)9781728196817
Parallel mechanisms are becoming increasingly popular as subsystems in various robots due to their superior stiffness, payload-to-weight ratio, and dynamic properties. The serial connection of parallel subsystems leads to series-parallel hybrid robots, which are more difficult to model and control than serial or tree-type systems. At the same time, WholeBody Control (WBC) has become the method of choice in the control of robots with redundant degrees of freedom, e.g., legged robots. However, most state-of-the-art WBC frameworks can only deal with serial or tree-type robot topologies. In this paper, we describe a computationally efficient framework for WholeBody Control of series-parallel hybrid robots subjected to a large number of holonomic constraints. In contrast to existing WBC frameworks, our approach describes the optimization problem in the actuation space of a series-parallel robot, which provides better exploitation of the feasible workspace, higher accuracy, and more transparent behavior near singularities. We evaluate the proposed framework on two different humanoids with series-parallel architecture and compare its performance to a WBC approach for tree-type robots.
Computers are capable of learning from data and observations and providing solutions to real-life complex problems, following the same reasoning approach of human experts in various fields. This book endows a rich col...
详细信息
ISBN:
(数字)9783031441271
ISBN:
(纸本)9783031441264;9783031441295
Computers are capable of learning from data and observations and providing solutions to real-life complex problems, following the same reasoning approach of human experts in various fields. This book endows a rich collection of applications in widespread areas. Among the areas addressed in this book are computationalintelligence Principles andTechniques; CI in Manufacturing, Engineering, and Industry; CI in Recognition and Processing; CI in robotics and automation; CI in Communications and Networking; CI in Traditional Vehicles, Electric Vehicles, and Autonomous Vehicles; CI in Smart Cities and Smart Energy Systems; and CI in Finance, Business, Economics, and Education. These areas span many topics including repetitive manufacturing, discrete manufacturing, process manufacturing, electronic systems, speech recognition, pattern recognition, signal processing, image processing, industrial monitoring, vision systems for automation and robotics, cooperative and network robotics, perception, planning, control, urban traffic networks control, vehicle-to-roadside communications, smart buildings, smart urbanism, smart infrastructure, smart connected communities, smart energy, security, arts, and music.
An sliding mode controller design for missiles guidance law is designed under the presence of target maneuvering. To reduce the chattering in sliding mode control, constitute a continuous function instead of signal fu...
详细信息
ISBN:
(纸本)9787121113154
An sliding mode controller design for missiles guidance law is designed under the presence of target maneuvering. To reduce the chattering in sliding mode control, constitute a continuous function instead of signal function which guarantees the practicability of the control scheme. Simulation shows the well tracking performance of the controller. Chattering is erased and the robustness is intensified.
Path planning and collision avoidance are challenging in complex and highly variable environments due to the limited horizon of events. In literature, there are multiple model- and learning-based approaches that requi...
详细信息
ISBN:
(纸本)9781728190778
Path planning and collision avoidance are challenging in complex and highly variable environments due to the limited horizon of events. In literature, there are multiple model- and learning-based approaches that require signilicant computational resources to be effectively deployed and they may have limited generality. We propose a planning algorithm based on a globally stable passive controller that can plan smooth trajectories using limited computational resources in challenging environmental conditions. The architecture combines the recently proposed fractal impedance controller with elastic bands and regions of finite time invariance. As the method is based on an impedance controller, it can also be used directly as a force/torque controller. We validated our method in simulation to analyse the ability of interactive navigation in challenging concave domains via the issuing of via-points, and its robustness to low bandwidth feedback. A swarm simulation using 11 agents validated the scalability of the proposed method. We have performed hardware experiments on a holonomic wheeled platform validating smoothness and robustness of interaction with dynamic agents (i.e., humans and robots). The computational complexity of the proposed local planner enables deployment with low-power micro-controllers lowering the energy consumption compared to other methods that rely upon numeric optimisation.
Hilbert-Huang Transform(HHT) is widely used in extracting the instantaneous characteristics of signals. If using Hilbert Transform to deal with signals, the signals must Satisfy certain conditions, or else there will ...
详细信息
The technology of software automatic generation in the field of monitoring system has been studied. A set of technologies and methods of software automatic generation for a specific field has been proposed. It can be ...
详细信息
暂无评论