Your browser doesn't support javascript.
Mostrar: 20 | 50 | 100
Resultados 1 - 2 de 2
Mais filtros

Base de dados
Intervalo de ano de publicação
Sensors (Basel) ; 20(17)2020 Aug 27.
Artigo em Inglês | MEDLINE | ID: mdl-32867080


It is challenging to avoid obstacles safely and efficiently for multiple robots of different shapes in distributed and communication-free scenarios, where robots do not communicate with each other and only sense other robots' positions and obstacles around them. Most existing multi-robot collision avoidance systems either require communication between robots or require expensive movement data of other robots, like velocities, accelerations and paths. In this paper, we propose a map-based deep reinforcement learning approach for multi-robot collision avoidance in a distributed and communication-free environment. We use the egocentric local grid map of a robot to represent the environmental information around it including its shape and observable appearances of other robots and obstacles, which can be easily generated by using multiple sensors or sensor fusion. Then we apply the distributed proximal policy optimization (DPPO) algorithm to train a convolutional neural network that directly maps three frames of egocentric local grid maps and the robot's relative local goal positions into low-level robot control commands. Compared to other methods, the map-based approach is more robust to noisy sensor data, does not require robots' movement data and considers sizes and shapes of related robots, which make it to be more efficient and easier to be deployed to real robots. We first train the neural network in a specified simulator of multiple mobile robots using DPPO, where a multi-stage curriculum learning strategy for multiple scenarios is used to improve the performance. Then we deploy the trained model to real robots to perform collision avoidance in their navigation without tedious parameter tuning. We evaluate the approach with multiple scenarios both in the simulator and on four differential-drive mobile robots in the real world. Both qualitative and quantitative experiments show that our approach is efficient and outperforms existing DRL-based approaches in many indicators. We also conduct ablation studies showing the positive effects of using egocentric grid maps and multi-stage curriculum learning.

Peptides ; 99: 189-194, 2018 01.
Artigo em Inglês | MEDLINE | ID: mdl-29024714


This study attempted to incorporate the antibacterial peptide nisin into an etch-and-rinse dental adhesive to evaluate the antibacterial activity of the modified adhesive against Streptococcus mutans and the bond strength. Single Bond 2 was used as a negative control, and nisin was incorporated at 1%, 3%, and 5% (w/v). The antibacterial activity against S. mutans was evaluated using the film contact test, the agar diffusion test, XTT assays and confocal laser scanning microscopy (CLSM). The microtensile bond strength (µTBS) of the modified dental adhesive was also evaluated. The cured nisin-incorporated dental adhesive exhibited a significant inhibitory effect on the growth of S. mutans (P<0.05), and the inhibitory effect was strengthened as the nisin concentration increased (P<0.05). However, no significant differences in the agar diffusion test were found for the cured nisin-incorporated adhesives compared with the control group. Based on XTT results and CLSM images, the cured nisin-incorporated adhesive interfered with the adherence of S. mutans and the integrity of its biofilms (P<0.05). Compared with the control group, the 1% nisin group did not exhibit a significant difference in µTBS (P>0.05), whereas the 3% and 5% nisin groups displayed decreased bond strength (P<0.05).

Antibacterianos , Cimentos Dentários , Nisina , Streptococcus mutans/crescimento & desenvolvimento , Antibacterianos/química , Antibacterianos/farmacologia , Cimentos Dentários/síntese química , Cimentos Dentários/química , Cimentos Dentários/farmacologia , Nisina/química , Nisina/farmacologia