Artificial intelligence (AI) is used more heavily in agricultural applications.Yet, the lack of wireless-fidelity (Wi-Fi) connections on agricultural fields makes AI cloud services unavailable.Consequently, AI models have to be processed directly on the edge.In this paper, we evaluate state-of-the-art detection algorithms for their use in agriculture, in particular plant detection.Thus, this paper presents the CornWeed data set, which has been recorded on farm machines, showing labelled maize crops and weeds for plant detection.The paper provides accuracies for the state-of-the-art detection algorithms on the CornWeed data set, as well as frames per second (FPS) metrics for the considered networks on multiple edge devices.Moreover, for the FPS analysis, the detection algorithms are converted to open neural network exchange (ONNX) and TensoRT engine files as they could be used as future standards for model exchange.

For swarm systems, distributed processing is of paramount importance and Bayesian methods are preferred for their robustness. Existing distributed sparse Bayesian learning (SBL) methods rely on the automatic relevance determination (ARD), which involves a computationally complex reweighted l1-norm optimization, or they use loopy belief propagation, which is not guaranteed to converge. Hence, this paper looks into the fast marginal likelihood maximization (FMLM) method to develop a faster distributed SBL version. The proposed method has a low communication overhead, and can be distributed by simple consensus methods. The performed simulations indicate a better performance compared with the distributed ARD version, yet the same performance as the FMLM.

In processing spatially distributed data, multi-agent robotic platforms equipped with sensors and computing capabilities are gaining interest for applications in inhospitable environments. In this work an algorithm for a distributed realization of sparse bayesian learning (SBL) is discussed for learning a static spatial process with the splitting-over-features approach over a network of interconnected agents. The observed process is modeled as a superposition of weighted kernel functions, or features as we call it, centered at the agent's measurement locations. SBL is then used to determine which feature is relevant for representing the spatial process. Using upper bounding convex functions, the SBL parameter estimation is formulated as ℓ1-norm constrained optimization, which is solved distributively using alternating direction method of multipliers (ADMM) and averaged consensus. The performance of the method is demonstrated by processing real magnetic field data collected in a laboratory.

Exploration is a crucial problem in safety of life applications, such as search and rescue missions. Gaussian processes constitute an interesting underlying data model that leverages the spatial correlations of the process to be explored to reduce the required sampling of data. Furthermore, multi-agent approaches offer well known advantages for exploration. Previous decentralized multi-agent exploration algorithms that use Gaussian processes as underlying data model, have only been validated through simulations. However, the implementation of an exploration algorithm brings difficulties that were not tackle yet. In this work, we propose an exploration algorithm that deals with the following challenges: (i) which information to transmit to achieve multi-agent coordination; (ii) how to implement a light-weight collision avoidance; (iii) how to learn the data's model without prior information. We validate our algorithm with two experiments employing real robots. First, we explore the magnetic field intensity with a ground-based robot. Second, two quadcopters equipped with an ultrasound sensor explore a terrain profile. We show that our algorithm outperforms a meander and a random trajectory, as well as we are able to learn the data's model online while exploring.