Safe, socially compliant, and efficient navigation of low-speed autonomous vehicles (AVs) in pedestrian-rich environments necessitates considering pedestrians' future positions and interactions with the vehicle an...
详细信息
Safe, socially compliant, and efficient navigation of low-speed autonomous vehicles (AVs) in pedestrian-rich environments necessitates considering pedestrians' future positions and interactions with the vehicle and others. Despite the inevitable uncertainties associated with pedestrians' predicted trajectories due to their unobserved states (e.g., intent), existing deep reinforcement learning (DRL) algorithms for crowd navigation often neglect these uncertainties when using predicted trajectories to guide policy learning. This omission limits the usability of predictions when diverging from ground truth. This work introduces an integrated prediction and planning approach that incorporates the uncertainties of predicted pedestrian states in the training of a model-free DRL algorithm. A novel reward function encourages the AV to respect pedestrians' personal space, decrease speed during close approaches, and minimize the collision probability with their predicted paths. Unlike previous DRL methods, our model, designed for AV operation in crowded spaces, is trained in a novel simulation environment that reflects realistic pedestrian behaviour in a shared space with vehicles. Results show a 40% decrease in collision rate and a 15% increase in minimum distance to pedestrians compared to the state of the art model that does not account for prediction uncertainty. Additionally, the approach outperforms model predictive control methods that incorporate the same prediction uncertainties in terms of both performance and computational time, while producing trajectories closer to human drivers in similar scenarios. IEEE
The presence of long-range interactions is crucial in distinguishing between abstract complex networks and wave *** photonics,because electromagnetic interactions between optical elements generally decay rapidly with ...
详细信息
The presence of long-range interactions is crucial in distinguishing between abstract complex networks and wave *** photonics,because electromagnetic interactions between optical elements generally decay rapidly with spatial distance,most wave phenomena are modeled with neighboring interactions,which account for only a small part of conceptually possible ***,we explore the impact of substantial long-range interactions in topological *** demonstrate that a crystalline structure,characterized by long-range interactions in the absence of neighboring ones,can be interpreted as an overlapped *** overlap model facilitates the realization of higher values of topological invariants while maintaining bandgap width in photonic topological *** breaking of topology-bandgap tradeoff enables topologically protected multichannel signal processing with broad *** practically accessible system parameters,the result paves the way to the extension of topological physics to network science.
We consider a power system whose electric demand pertaining to freshwater production is high(high freshwater electric demand),as in the Middle East,and investigate the tradeoff of storing freshwater in tanks versus st...
详细信息
We consider a power system whose electric demand pertaining to freshwater production is high(high freshwater electric demand),as in the Middle East,and investigate the tradeoff of storing freshwater in tanks versus storing electricity in batteries at the day-ahead operation *** storing freshwater and storing electricity increase the actual electric demand at valley hours and decrease it at peak hours,which is generally beneficial in term of cost and ***,to what extent?We analyze this question considering three power systems with different generation-mix configurations,i.e.,a thermal-dominated mix,a renewable-dominated one,and a fully renewable *** generation-mix configurations are inspired by how power systems may evolve in different countries in the Middle *** production uncertainty is compactly modeled using chance *** draw conclusions on how both storage facilities(freshwater and electricity)complement each other to render an optimal operation of the power system.
In this paper, a 13-level circuit topology is proposed, which features a single dc source, extended linear modulation range, and a high ratio of output voltage levels to semiconductor devices. The proposed converter, ...
详细信息
In this paper, a 13-level circuit topology is proposed, which features a single dc source, extended linear modulation range, and a high ratio of output voltage levels to semiconductor devices. The proposed converter, which consists of a series-connected floating H-bridge (FHB) supplementing a five-level active neutral point clamped converter (5L-ANPC), can generate 13 pole voltage levels in the normal modulation region and 15 levels in the extended modulation region. The key performance improvements offered by the proposed topology are enhanced power quality, reduced losses, and increased power density. Whereas existing schemes with a similar circuit structure regulate the FHB to one-eighth of the dc-link voltage and only achieve nine levels, the proposed joint-phase redundancy balancing approach regulates the FHB stage to one-twelfth of the total dc-link voltage on a switching-frequency basis, thereby increasing output power quality while reducing the converter's cost and size without the need for multiple isolated supplies. Further, the proposed modulation scheme also allows for a switching frequency reduction of the higher voltage blocking 5L-ANPC stage by shifting the high-frequency switching to the low voltage blocking FHB stage, thus reducing losses. This work also evaluates operation in the topology's extended linear modulation range which is shown to be increased to 0.612 times the dc-link voltage (modulation index, M = 1.223) without limitations on load power factors, compared to the typical limit of to 0.577 times the dc-link voltage (M = 1.154) for non-boosting topologies such as 3L-ANPC and 5L-ANPC. The proposed converter uses boosting states enabled by the FHB in this extended modulation region, which increases the number of output levels to 15. The effectiveness of the proposed topology and capacitor balancing scheme is validated using experimental and analytical results. Based on experimental and analytical results, the proposed topology is shown to h
Delay/disruption tolerant networking(DTN) is proposed as a networking architecture to overcome challenging space communication characteristics for reliable data transmission service in presence of long propagation del...
详细信息
Delay/disruption tolerant networking(DTN) is proposed as a networking architecture to overcome challenging space communication characteristics for reliable data transmission service in presence of long propagation delays and/or lengthy link disruptions. Bundle protocol(BP) and Licklider Transmission Protocol(LTP) are the main key technologies for DTN. LTP red transmission offers a reliable transmission mechanism for space networks. One of the key metrics used to measure the performance of LTP in space applications is the end-to-end data delivery delay, which is influenced by factors such as the quality of spatial channels and the size of cross-layer packets. In this paper, an end-to-end reliable data delivery delay model of LTP red transmission is proposed using a roulette wheel algorithm, and the roulette wheel algorithm is more in line with the typical random characteristics in space networks. The proposed models are validated through real data transmission experiments on a semi-physical testing platform. Furthermore, the impact of cross-layer packet size on the performance of LTP reliable transmission is analyzed, with a focus on bundle size, block size, and segment size. The analysis and study results presented in this paper offer valuable contributions towards enhancing the reliability of LTP transmission in space communication scenarios.
Under perfect competition,marginal pricing results in short-term efficiency and the subsequent right short-term price ***,the main reason for the adoption of marginal pricing is not the above,but investment cost *** i...
详细信息
Under perfect competition,marginal pricing results in short-term efficiency and the subsequent right short-term price ***,the main reason for the adoption of marginal pricing is not the above,but investment cost *** is,the fact that the profits obtained by infra-marginal technologies(technologies whose production cost is below the marginal price)allow them just to recover their investment *** the other hand,if the perfect competition assumption is removed,investment over-recovery or under-recovery generally occurs for infra-marginal technologies.
Droplet microfluidics enable high-throughput screening,sequencing,and formulation of biological and chemical systems at the *** devices are generally fabricated in a soft polymer such as polydimethylsiloxane(PDMS).How...
详细信息
Droplet microfluidics enable high-throughput screening,sequencing,and formulation of biological and chemical systems at the *** devices are generally fabricated in a soft polymer such as polydimethylsiloxane(PDMS).However,developing design masks for PDMS devices can be a slow and expensive process,requiring an internal cleanroom facility or using an external ***,we present the first complete droplet-based component library using low-cost rapid prototyping and electrode *** fabrication method for droplet microfluidic devices costs less than$12 per device and a full design-build-test cycle can be completed within a *** microfluidic components for droplet generation,re-injection,picoinjection,anchoring,fluorescence sensing,and sorting were built and *** devices are biocompatible,low-cost,and *** show its ability to perform multistep workflows,these components were used to assemble droplet"pixel"arrays,where droplets were generated,sensed,sorted,and anchored onto a grid to produce images.
This paper proposes an empirical wavelet transform(EWT)based method for identification and analysis of sub-synchronous oscillation(SSO)modes in the power system using phasor measurement unit(PMU)*** phasors from PMUs ...
详细信息
This paper proposes an empirical wavelet transform(EWT)based method for identification and analysis of sub-synchronous oscillation(SSO)modes in the power system using phasor measurement unit(PMU)*** phasors from PMUs are preprocessed to check for the presence of *** the presence is established,the signal is decomposed using EWT and the parameters of the mono-components are estimated through Yoshida *** superiority of the proposed method is tested using test signals with known parameters and simulated using actual SSO signals from the Hami Power Grid in Northwest *** show the effectiveness of the proposed EWT-Yoshida method in detecting the SSO and estimating its parameters.
Across the world, the lack of proper healthcare resources in rural areas significantly impacts the physical and economic well-being of individuals living there. There is a need for multi-faceted solutions to help alle...
详细信息
High-dimensional and incomplete(HDI) matrices are primarily generated in all kinds of big-data-related practical applications. A latent factor analysis(LFA) model is capable of conducting efficient representation lear...
详细信息
High-dimensional and incomplete(HDI) matrices are primarily generated in all kinds of big-data-related practical applications. A latent factor analysis(LFA) model is capable of conducting efficient representation learning to an HDI matrix,whose hyper-parameter adaptation can be implemented through a particle swarm optimizer(PSO) to meet scalable ***, conventional PSO is limited by its premature issues,which leads to the accuracy loss of a resultant LFA model. To address this thorny issue, this study merges the information of each particle's state migration into its evolution process following the principle of a generalized momentum method for improving its search ability, thereby building a state-migration particle swarm optimizer(SPSO), whose theoretical convergence is rigorously proved in this study. It is then incorporated into an LFA model for implementing efficient hyper-parameter adaptation without accuracy loss. Experiments on six HDI matrices indicate that an SPSO-incorporated LFA model outperforms state-of-the-art LFA models in terms of prediction accuracy for missing data of an HDI matrix with competitive computational ***, SPSO's use ensures efficient and reliable hyper-parameter adaptation in an LFA model, thus ensuring practicality and accurate representation learning for HDI matrices.
暂无评论