Abstract
Proper waste management has been recognized as a tool for the green transition towards a more sustainable economy. For instance, most studies dealing with municipal solid wastes in the literature focus on environmental aspects, proposing new routes for recycling, composting and landfilling. However, there are other aspects to be improved in the systems that deal with municipal solid waste, especially in the transportation sector. Scholars have been exploring alternatives to improve the performance in waste collection tasks since the late 50s, for example, considering the waste collection problem as static. The transition from a static approach to a dynamic is necessary to increase the feasibility of the solution, requiring faster algorithms. Here we explore the improvement in the performance of the guided local search metaheuristic available in OR-Tools upon different execution times lower than 10 seconds to solve the capacitated waste collection problem. We show that increasing the execution time from 1 to 10 seconds can overcome savings of up to 1.5 km in the proposed system. Considering application in dynamic scenarios, the 9 s increase in execution time (from 1 to 10 s) would not hinder the algorithm's feasibility. Additionally, the assessment of the relation between performance in different execution times with the dataset's tightness revealed a correlation to be explored in more detail in future studies. The work done here is the first step towards a shift of paradigm from static scenarios in waste collection to dynamic route planning, with the execution time established according to the conclusions achieved in this study. © 2023 ITMA.

Abstract

Abstract
Recent developments in dexterous robotic manipulation technologies allowed for the design of very compact, yet capable, multi-fingered robotic hands. These can be designed to emulate the human touch and feel, reducing the aforementioned need for human expertise in highly detailed tasks. The presented work focused on the application of two simulation platforms Gazebo and MuJoCo - to a use-case of a Schunk Five Finger Robotic Hand, coupled to the UR5 collaborative manipulator. This allowed to assess the relative appropriateness of each of these platforms.

Abstract
Robotics and intelligent systems are key technologies to promote efficient and innovative applications in the most diverse domains (industry, healthcare, agriculture, construction, mobility, etc [...]

Abstract
Several thousand grapevine varieties exist, with even more naming identifiers. Adequate specialized labor is not available for proper classification or identification of grapevines, making the value of commercial vines uncertain. Traditional methods, such as genetic analysis or ampelometry, are time-consuming, expensive, and often require expert skills that are even rarer. New vision-based systems benefit from advanced and innovative technology and can be used by nonexperts in ampelometry. To this end, deep learning (DL) and machine learning (ML) approaches have been successfully applied for classification purposes. This work extends the state of the art by applying digital ampelometry techniques to larger grapevine varieties. We benchmarked MobileNet v2, ResNet-34, and VGG-11-BN DL classifiers to assess their ability for digital ampelography. In our experiment, all the models could identify the vines' varieties through the leaf with a weighted F1 score higher than 92%.

Abstract
Purpose: Visual perception enables robots to perceive the environment. Visual data is processed using computer vision algorithms that are usually time-expensive and require powerful devices to process the visual data in real-time, which is unfeasible for open-field robots with limited energy. This work benchmarks the performance of different heterogeneous platforms for object detection in real-time. This research benchmarks three architectures: embedded GPU-Graphical Processing Units (such as NVIDIA Jetson Nano 2 GB and 4 GB, and NVIDIA Jetson TX2), TPU-Tensor Processing Unit (such as Coral Dev Board TPU), and DPU-Deep Learning Processor Unit (such as in AMD-Xilinx ZCU104 Development Board, and AMD-Xilinx Kria KV260 Starter Kit). Methods: The authors used the RetinaNet ResNet-50 fine-tuned using the natural VineSet dataset. After the trained model was converted and compiled for target-specific hardware formats to improve the execution efficiency.Conclusions and Results: The platforms were assessed in terms of performance of the evaluation metrics and efficiency (time of inference). Graphical Processing Units (GPUs) were the slowest devices, running at 3 FPS to 5 FPS, and Field Programmable Gate Arrays (FPGAs) were the fastest devices, running at 14 FPS to 25 FPS. The efficiency of the Tensor Processing Unit (TPU) is irrelevant and similar to NVIDIA Jetson TX2. TPU and GPU are the most power-efficient, consuming about 5 W. The performance differences, in the evaluation metrics, across devices are irrelevant and have an F1 of about 70 % and mean Average Precision (mAP) of about 60 %.