Search

RGB-D sensors face multiple challenges operating under open-field environments because of their sensitivity to external perturbations such as radiation or rain. Multiple works are approaching the challenge of perceiving the 3D position of objects using monocular cameras. However, most of these works focus mainly on deep learning-based solutions, which are complex, data-driven, and difficult to predict. So, we aim to approach the problem of predicting the 3D objects' position using a Gaussian viewpoint estimator named best viewpoint estimator (BVE) powered by an extended Kalman filter (EKF). The algorithm proved efficient on the tasks and reached a maximum average Euclidean error of about 32 mm. The experiments were deployed and evaluated in MATLAB using artificial Gaussian noise. Future work aims to implement the system in a robotic system.

Performing tasks in agriculture, such as fruit monitoring or harvesting, requires perceiving the objects' spatial position. RGB-D cameras are limited under open-field environments due to lightning interferences. Therefore, in this study, we approach the use of Histogram Filters (Bayesian Discrete Filters) to estimate the position of tomatoes in the tomato plant. Two kernel filters were studied: the square kernel and the Gaussian kernel. The implemented algorithm was essayed in simulation, with and without Gaussian noise and random noise, and in a testbed at laboratory conditions. The algorithm reported a mean absolute error lower than 10 mm in simulation and 20 mm in the testbed at laboratory conditions with an assessing distance of about 0.5 m. So, the results are viable for real environments and should be improved at closer distances.

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). Method: 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 5W. 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 %.

In this work, first we prove that for any compact set $K\subset\mathbb{R}^{n}$ and any continuous function $\phi$ defined on $\partial K$, there exists a bounded weak solution in $C(\bar{\mathbb{R}^{n}\backslash K}) \cap C^1(\mathbb{R}^{n}\backslash K)$ to the exterior Dirichlet problem $$ \begin{cases} -{\rm div}\big(\,|\nabla u|^{p-2}A(\,|\nabla u|\,)\nabla u\,\big)=f & \text{ in }\, \mathbb{R}^n \backslash K \;\;\;\;\;\; u = \phi & \text{ on } \partial K \end{cases} $$ provided $p > n$, $A$ satisfies some growth conditions and $f\in L^{\infty}(\mathbb{R}^n)$ meets a suitable pointwise decay rate. We obtain thereafter the existence of the limit at the infinity for solutions to this problem, for any $p\in(1,+\infty)$ and $n\geq2$. Moreover, for $p > n$ we can show that the solutions converge at some rate and for $p

The development of robotic solutions for agriculture requires advanced perception capabilities that can work reliably in any crop stage. For example, to automatise the tomato harvesting process in greenhouses, the visual perception system needs to detect the tomato in any life cycle stage (flower to the ripe tomato). The state-of-the-art for visual tomato detection focuses mainly on ripe tomato, which has a distinctive colour from the background. This paper contributes with an annotated visual dataset of green and reddish tomatoes. This kind of dataset is uncommon and not available for research purposes. This will enable further developments in edge artificial intelligence for in situ and in real-time visual tomato detection required for the development of harvesting robots. Considering this dataset, five deep learning models were selected, trained and benchmarked to detect green and reddish tomatoes grown in greenhouses. Considering our robotic platform specifications, only the Single-Shot MultiBox Detector (SSD) and YOLO architectures were considered. The results proved that the system can detect green and reddish tomatoes, even those occluded by leaves. SSD MobileNet v2 had the best performance when compared against SSD Inception v2, SSD ResNet 50, SSD ResNet 101 and YOLOv4 Tiny, reaching an F1-score of 66.15%, an mAP of 51.46% and an inference time of 16.44 ms with the NVIDIA Turing Architecture platform, an NVIDIA Tesla T4, with 12 GB. YOLOv4 Tiny also had impressive results, mainly concerning inferring times of about 5 ms., Comment: Dataset at DOI:10.25747/pc1e-nk92

This paper presents a novel application of tensegrity systems as lightweight and noninvasive braces for seismically resistant structures. The analyzed braces consist of D-bar systems equipped with shape memory alloy cables with superelastic response. These structures are able to markedly amplify the applied longitudinal displacements in the transverse direction, thus allowing for considerably large deformations of the SMA cables and high energy dissipation. The mechanics and the application of tensegrity braces for the reinforcement of anti-seismic structures are presented. A comparative study matches the seismic response of the analyzed systems with that of devices employing fluid viscous dampers. The results highlight the fact that D-bar units can be profitably employed as building blocks for innovative bracing systems, whose energy dissipation properties can easily surpass those of conventional anti-seismic braces., Comment: Preprint of Extreme Mechanics Letters (ISSN:2352-4316)