MC for Agriculture: A Framework for Nature-inspired Sustainable Pest Control

In agriculture, molecular communication (MC) is envisioned as a framework to address critical challenges such as smart pest control. While conventional approaches mostly rely on synthetic plant protection products, posing high risks for the environment, harnessing plant signaling processes can lead to innovative approaches for nature-inspired sustainable pest control. In this paper, we investigate an approach for sustainable pest control and reveal how the MC paradigm can be employed for analysis and optimization. In particular, we consider a system where herbivore-induced plant volatiles (HIPVs), specifically methyl salicylate (MeSA), is encapsulated into microspheres deployed on deployed on plant leaves. The controlled release of MeSA from the microspheres, acting as transmitters (TXs), supports pest deterrence and antagonist attraction, providing an eco-friendly alternative to synthetic plant protection products. Based on experimental data, we investigate the MeSA release kinetics and obtain an analytical model. To describe the propagation of MeSA in farming environments, we employ a three dimensional (3D) advection-diffusion model, incorporating realistic wind fields which are predominantly affecting particle propagation, and solve it by a finite difference method (FDM). The proposed model is used to investigate the MeSA distribution for different TX arrangements, representing different practical microsphere deployment strategies. Moreover, we introduce the coverage effectiveness index (CEI) as a novel metric to quantify the environmental coverage of MeSA. This analysis offers valuable guidance for the practical development of microspheres and their deployment aimed at enhancing coverage and, consequently, the attraction of antagonistic insects.

LMFormer: Lane based Motion Prediction Transformer

Motion prediction plays an important role in autonomous driving. This study presents LMFormer, a lane-aware transformer network for trajectory prediction tasks. In contrast to previous studies, our work provides a simple mechanism to dynamically prioritize the lanes and shows that such a mechanism introduces explainability into the learning behavior of the network. Additionally, LMFormer uses the lane connection information at intersections, lane merges, and lane splits, in order to learn long-range dependency in lane structure. Moreover, we also address the issue of refining the predicted trajectories and propose an efficient method for iterative refinement through stacked transformer layers. For benchmarking, we evaluate LMFormer on the nuScenes dataset and demonstrate that it achieves SOTA performance across multiple metrics. Furthermore, the Deep Scenario dataset is used to not only illustrate cross-dataset network performance but also the unification capabilities of LMFormer to train on multiple datasets and achieve better performance.

CASPFormer: Trajectory Prediction from BEV Images with Deformable Attention

Motion prediction is an important aspect for Autonomous Driving (AD) and Advance Driver Assistance Systems (ADAS). Current state-of-the-art motion prediction methods rely on High Definition (HD) maps for capturing the surrounding context of the ego vehicle. Such systems lack scalability in real-world deployment as HD maps are expensive to produce and update in real-time. To overcome this issue, we propose Context Aware Scene Prediction Transformer (CASPFormer), which can perform multi-modal motion prediction from rasterized Bird-Eye-View (BEV) images. Our system can be integrated with any upstream perception module that is capable of generating BEV images. Moreover, CASPFormer directly decodes vectorized trajectories without any postprocessing. Trajectories are decoded recurrently using deformable attention, as it is computationally efficient and provides the network with the ability to focus its attention on the important spatial locations of the BEV images. In addition, we also address the issue of mode collapse for generating multiple scene-consistent trajectories by incorporating learnable mode queries. We evaluate our model on the nuScenes dataset and show that it reaches state-of-the-art across multiple metrics