In target tracking with mobile multi-sensorsystems, sensor deployment impacts the observation capabilities and the resulting state estimation quality. Based on a partially observable Markov decision process (POMDP) f...
详细信息
ISBN:
(数字)9781665479271
ISBN:
(纸本)9781665479271
In target tracking with mobile multi-sensorsystems, sensor deployment impacts the observation capabilities and the resulting state estimation quality. Based on a partially observable Markov decision process (POMDP) formulation comprised of the observable sensor dynamics, unobservable target states, and accompanying observation laws, we present a distributed information-driven solution approach to the multi-agent target tracking problem, namely, sequential multi-agent nominal belief-state optimization (SMA-NBO). SMA-NBO seeks to minimize the expected tracking error via receding horizon control including a heuristic expected cost-to-go (HECTG). SMA-NBO incorporates a computationally efficient approximation of the target belief-state over the horizon. The agent-byagent decision-making is capable of leveraging on-board (edge) compute for selecting (sub-optimal) target-tracking maneuvers exhibiting non-myopic cooperative fleet behavior. The optimization problem explicitly incorporates semantic information defining target occlusions from a world model. To illustrate the efficacy of our approach, a random occlusion forest environment is simulated. SMA-NBO is compared to other baseline approaches. The simulation results show SMA-NBO 1) maintains tracking performance and reduces the computational cost by replacing the calculation of the expected target trajectory with a single sample trajectory based on maximum a posteriori estimation;2) generates cooperative fleet decision by sequentially optimizing single-agent policy with efficient usage of other agents' policy of intent;3) aptly incorporates the multiple weighted trace penalty (MWTP) HECTG, which improves tracking performance with a computationally efficient heuristic.
Cooperative Intelligent Transportation systems envision the integration of cooperative intelligence as a key operational part of autonomous driving. In this way, a fleet or swarm of Connected and Automated Vehicles co...
详细信息
ISBN:
(数字)9781728175683
ISBN:
(纸本)9781728175683
Cooperative Intelligent Transportation systems envision the integration of cooperative intelligence as a key operational part of autonomous driving. In this way, a fleet or swarm of Connected and Automated Vehicles collectively coordinates its driving actions in order to maximize its performance. To realize this ambition, vehicles need to be fully location-aware of their surrounding environment, through distributed AI intelligence. Motivated by this requirement, we develop in this paper a distributed cooperative awareness scheme which performs multimodal fusion of heterogeneous sensor sources along with V2V communication information, using graph Laplacian matrix and Least-Mean-Squares algorithm. The intuition behind our approach is that neighboring vehicles are interested in estimating common positions of other vehicles. We build upon our previous work on global awareness though local information diffusion, and prove that the proposed distributed framework is able to address highly efficient the case of lacking any information about other networked vehicles. More specifically, our approach achieves high enough convergence speed as well as location accuracy. The evaluation study has been performed in CARLA autonomous driving simulator and verifies the proposed method's benefits over other related solutions.
The use of wearable devices in healthcare has become increasingly prevalent, with a focus on monitoring chronic diseases such as heart rate. Researchers have employed various methods, including machine learning, to an...
详细信息
Economic dispatch for the microgrid (MG) is better adapted to the needs of a system in actual operation in the current scenario because it not only takes into account the scheduling cycle's lowest cost but also co...
详细信息
The proliferation of distributed energy resources has heightened the interactions between transmission and distribution (T&D) systems, necessitating novel analyses for the reliable operation and planning of interc...
详细信息
Compared with the probability hypothesis density (PHD) filter for sets of targets, the trajectory probability hypothesis density (TPHD) filter can estimate the sets of trajectories in a principle way and has better ta...
详细信息
ISBN:
(数字)9781665460262
ISBN:
(纸本)9781665460262
Compared with the probability hypothesis density (PHD) filter for sets of targets, the trajectory probability hypothesis density (TPHD) filter can estimate the sets of trajectories in a principle way and has better target tracking performance. This paper aims at extending the TPHD filter to distributed multi-target tracking (MTT) for the multi-sensor system. However, in the trajectory set based distributed fusion implementation, the trajectory state difference phenomenon makes the clustering and merging techniques unfeasible in trajectory state space. To address this problem, this paper studies the space decomposition of the TPHD and proposes a distributed MTT method based on the TPHD filter with the weighted arithmetic average (WAA) fusion rule. First, we prove the rationality of the space decomposition in the posterior density of the TPHD filter. Then, based on the proposed property, we derive the WAA fusion formulation of the TPHD filter by minimizing the weighted sum of Kullback-Leibler divergences (KLD) from local posterior densities, and develop the analytical Gaussian mixture (GM) implementation with the L-scan approximation. Numerical results demonstrate the efficacy of the proposed fusion method.
While conventional measures of Situation Awareness (SA) focus on its adequacy in supporting decisions, fully exploiting information being returned by teams of unmanned aerial vehicles (UAVs) requires close attention t...
详细信息
Due to the rise in penetration of distributed energy resources (DERs) and energy storage systems (ESSs) into the microgrid (μG) system, the abrupt disconnections of DERs and ESSs might have an effect on the stability...
详细信息
This article explores the utilization of the processing power of GPUs using CUDA computation for real-time aggregation of multi-sensor data and detection of 3D objects using parallel clustering algorithms. The purpose...
详细信息
ISBN:
(纸本)9781665464376
This article explores the utilization of the processing power of GPUs using CUDA computation for real-time aggregation of multi-sensor data and detection of 3D objects using parallel clustering algorithms. The purpose is to implement an algorithm that fuses raw lidar point cloud data and 2D camera image object detections to produce 3D object clusters in a lidar point cloud. Most of the computation has been implemented using CUDA parallelism to investigate the capability of GPU devices in this task, which is a common challenge in automated driving. The results indicate that processing times can be optimized within the algorithm, which is crucial when considering the large amounts of data provided by lidar and camera-based systems. The algorithm can perform inference on the Jetson Xavier AGX at rates of similar to 20 to similar to 220 ms depending on the number of objects and their corresponding point amounts in the KITTI dataset.
This paper is devoted to the problem of data processing management in fog- and edge-computing environments. The main issue of task planning is that the environments of the fog and edge network tiers are dynamic and he...
详细信息
暂无评论