With recent advancements in industrial robots, educating students in new technologies and preparing them for the future is imperative. However, access to industrial robots for teaching poses challenges, such as the hi...
详细信息
With the pervasive integration of artificial intelligence into all aspects of human life, talent emerges as a primary resource. Upon analysing the current state of talent training in higher education institutions, iss...
详细信息
In the application scenario of robot autonomous tasks, the robot needs to be able to complete calibration online and automatically to achieve self-maintenance, which differs from traditional robot hand-eye calibration...
详细信息
Reinforcement Learning (RL), a method of learning skills through trial-and-error, has been successfully used in many robotics applications in recent years. We combine manipulation primitives (MPs), behavior trees (BTs...
详细信息
In this paper, Prioritized Experience Replay (PER) strategy and Long Short Term Memory (LSTM) neural network are introduced to the path planning process of mobile robots, which solves the problems of slow convergence ...
详细信息
With recent advancements in industrial robots, educating students in new technologies and preparing them for the future is imperative. However, access to industrial robots for teaching poses challenges, such as the hi...
详细信息
In recent years, Deep Reinforcement Learning (DRL) has emerged as a competitive approach for mobile robot navigation. However, training DRL agents often comes at the cost of difficult and tedious training procedures i...
In recent years, Deep Reinforcement Learning (DRL) has emerged as a competitive approach for mobile robot navigation. However, training DRL agents often comes at the cost of difficult and tedious training procedures in which powerful hardware is required to conduct oftentimes long training runs. Especially, for complex environments, this proves to be a major bottleneck for widespread adoption of DRL approaches into industries. In this paper we integrate an efficient 2D simulator into the Arena-Rosnav framework of our previous work as an alternative simulation platform to train and develop DRL agents. Therefore, we utilized the provided API to integrate necessary components into the ecosystem of Arena-Rosnav. We evaluated our simulator by training a DRL agent within that platform and compared the training and navigational performance against the baseline 2D simulator Flatland, which is the default simulating platform of Arena-Rosnav. Results demonstrate that using our Arena2D simulator results in substantially faster training times and in some scenarios better agents. This proves to be an important step towards resource-efficient DRL training, which accelerates training times and improve the development cycle of DRL agents for navigation tasks. We made our simulator openly available at https://***/Arena-Rosnav/arena2d.
The focus of this paper is to address a novel control technique for stability and transparency analysis of bilateral telerobotic systems in the presence of data loss and time delay in the communication channel. Differ...
详细信息
The focus of this paper is to address a novel control technique for stability and transparency analysis of bilateral telerobotic systems in the presence of data loss and time delay in the communication channel. Different control strategies have been reported to compensate the effects of time delay in the communication channel;however, most of them result in poor performance under data loss. First, a model for data loss is proposed using a finite series representation of a set of periodic continuous *** improve the performance and data reconstruction, a holder circuits is also introduced. The passivity of the overall system is provided via the wave variable technique based on the proposed model for the data loss. The stability analysis of the system is then derived using the Lyapunov theorem under the time delay and the data loss. Finally, experimental results are given to illustrate the capability of the proposed control technique.
Robotic competitions stand as platforms to propel the forefront of robotics research while nurturing STEM education, serving as hubs of both applied research and scientific innovation. In Portugal, the Portuguese Robo...
详细信息
ISBN:
(数字)9798350352344
ISBN:
(纸本)9798350352351
Robotic competitions stand as platforms to propel the forefront of robotics research while nurturing STEM education, serving as hubs of both applied research and scientific innovation. In Portugal, the Portuguese robotics Open (FNR) is an event with several robotic competitions, including the Robot@Factory 4.0 competition. This competition presents an example of deploying autonomous robots on a factory shop floor. Although the literature has works proposing frameworks for the original version of the Robot@Factory competition, none of them proposes a system framework for the Robot@Factory 4.0 version that presents the hardware, firmware, and software to complete the competition and achieve autonomous navigation. This paper proposes a complete robotic framework for the Robot@Factory 4.0 competition that is modular and open-access, enabling future participants to use and improve it in future editions. This work is the culmination of all the knowledge acquired by winning the 2022 and 2023 editions of the competition.
This paper proposes a novel approach to automatically generate labeled training data for predicting parallel-jaw grasps from stereo-matched depth images. We generate realistic depth images using Semi-Global Matching t...
详细信息
ISBN:
(纸本)9781665436854
This paper proposes a novel approach to automatically generate labeled training data for predicting parallel-jaw grasps from stereo-matched depth images. We generate realistic depth images using Semi-Global Matching to compute disparity maps from synthetic data, which allows producing images that mimic the typical artifacts from real stereo matching in our data, thus reducing the gap from simulation to real execution. Our pipeline automatically generates grasp annotations for single or multiple objects on the synthetically rendered scenes, avoiding any manual image pre-processing steps such as inpainting or denoising. The labeled data is then used to train a CNN-model that predicts parallel-jaw grasps, even in scenarios with large amount of unknown depth values. We further show that scene properties such as the presence of obstacles (a bin, for instance) can be added to our pipeline, and the training process results in grasp prediction success rates of up to 90%.
暂无评论