Uncertainty quantification is a vital aspect of explainable artificial intelligence that fosters clinician trust in medical applications and facilitates timely interventions, leading to safer and more reliable outcome...
详细信息
Autonomous driving is a highly anticipated approach toward eliminating roadway fatalities. At the same time, the bar for safety is both high and costly to verify. This work considers the role of remotely-located human...
详细信息
Evolutionary algorithms have been used to evolve a population of actors to generate diverse experiences for training reinforcement learning agents, which helps to tackle the temporal credit assignment problem and impr...
Evolutionary algorithms have been used to evolve a population of actors to generate diverse experiences for training reinforcement learning agents, which helps to tackle the temporal credit assignment problem and improves the exploration efficiency. However, when adapting this approach to address constrained problems, balancing the trade-off between the reward and constraint violation is hard. In this paper, we propose a novel evolutionary constrained reinforcement learning (ECRL) algorithm, which adaptively balances the reward and constraint violation with stochastic ranking, and at the same time, restricts the policy's behaviour by maintaining a set of Lagrange relaxation coefficients with a constraint buffer. Extensive experiments on robotic control benchmarks show that our ECRL achieves outstanding performance compared to state-of-the-art algorithms. Ablation analysis shows the benefits of introducing stochastic ranking and constraint buffer.
Targeting the notorious cumulative drift errors in NeRF SLAM, we propose a Semantic-guided Loop Closure using Shared Latent Code, dubbed SLC2-SLAM. We argue that latent codes stored in many NeRF SLAM systems are not f...
详细信息
This paper focuses on discovering the impact of communication mode allocation on communication efficiency in the vehicle communication networks. To be specific, Markov decision process and reinforcement learning are a...
详细信息
A common task for unmanned aerial vehicles (UAVs) is wide area search using an onboard camera with an object detection model. However, constraints of flight time, camera optics, and onboard compute, particularly in ti...
详细信息
ISBN:
(数字)9798331513283
ISBN:
(纸本)9798331513290
A common task for unmanned aerial vehicles (UAVs) is wide area search using an onboard camera with an object detection model. However, constraints of flight time, camera optics, and onboard compute, particularly in time sensitive applications like search and rescue, requires tradeoffs in strategies that balance precision and speed. To address these needs, we propose a novel method for evaluating coverage path plans by estimating the probabilities of detection and false alarm for ground targets for a set of poses that the UAV can reach in the search domain. To demonstrate our method, we evaluate trajectories for various coverage path plans flown by a UAV in a high-fidelity simulation.
A 16-dimensional Voronoi constellation concatenated with multilevel coding is experimentally demonstrated over a 50 km four-core fiber transmission system. The proposed scheme reduces the required launch power by 6 dB...
详细信息
Eco-driving emerges as a cost-effective and efficient strategy to mitigate greenhouse gas emissions in urban transportation networks. Acknowledging the persuasive influence of incentives in shaping driver behavior, th...
详细信息
In a predefined geographical field, a group of sensor nodes communicating wirelessly form a Wireless Sensor Network (WSN). The sensors' goal is to upload the sensed data to the control station to determine if any ...
In a predefined geographical field, a group of sensor nodes communicating wirelessly form a Wireless Sensor Network (WSN). The sensors' goal is to upload the sensed data to the control station to determine if any immediate action should be taken or to analyze and monitor the situation. In clustering algorithms, the sensors are grouped as clusters, where each cluster has one sensor selected as the cluster head (CH) responsible for all inter-cluster communication. In a crisis scenario, the CH might be non-functional, resulting in a disconnected cluster. An enhanced WSN weighted cluster routing scheme is proposed in this paper. A cluster index based on distance, rewarding index, and energy is used to select the CH and cluster members (CM). The proposed scheme aims at ensuring that the data is uploaded even though the CH is non-functional by selecting a redundant CH for every node. Therefore, no matter how many sensors are inactive, a CH is still selected to ensure inter-cluster communication. The delays generated in the proposed routing scheme are studied using MATLAB simulation. In addition, the effect of different weights is studied on the delay.
暂无评论