Search for: All records

Trajectory prediction forecasts nearby agents’ moves based on their historical trajectories. Accurate trajectory prediction (or prediction in short) is crucial for autonomous vehicles (AVs). Existing attacks compromise the prediction model of a victim AV by directly manipulating the historical trajectory of an attacker AV, which has limited real-world applicability. This paper, for the first time, explores an indirect attack approach that induces prediction errors via attacks against the perception module of a victim AV. Although it has been shown that physically realizable attacks against LiDAR-based perception are possible by placing a few objects at strategic locations, it is still an open challenge to find an object location from the vast search space in order to launch effective attacks against prediction under varying victim AV velocities. Through analysis, we observe that a prediction model is prone to an attack focusing on a single point in the scene. Consequently, we propose a novel two-stage attack framework to realize the single-point attack. The first stage of predictionside attack efficiently identifies, guided by the distribution of detection results under object-based attacks against perception, the state perturbations for the prediction model that are effective and velocity-insensitive. In the second stage of location matching, we match the feasible object locations with the found state perturbations. Our evaluation using a public autonomous driving dataset shows that our attack causes a collision rate of up to 63% and various hazardous responses of the victim AV. The effectiveness of our attack is also demonstrated on a real testbed car 1. To the best of our knowledge, this study is the first security analysis spanning from LiDARbased perception to prediction in autonomous driving, leading to a realistic attack on prediction. To counteract the proposed attack, potential defenses are discussed. 

Comprehending the impact of wildfire smoke on photovoltaic (PV) systems is of utmost importance in ensuring the dependability and consistency of power systems, particularly due to the growing prevalence of PV installations and the occurrence of wildfires. Nevertheless, this issue has not received extensive investigation within the current literature. A major obstacle in studying this phenomenon lies in accurately quantifying the impact of smoke. Conventional techniques such as aerosol optical depth (AOD) and PM 2.5 are inadequate for accurately assessing the influence of wildfire smoke on PV systems due to the complex interplay of smoke elevation, dynamics, and nonlinear effects on the solar spectral irradiance. To address this challenge, a new methodology is developed in this research that employs the optical properties of wildfire smoke. This approach utilizes the spectral response (SR) of PV devices to estimate the theoretical reduction in PV power output. The findings of this study enable precise measurement of the power output reduction caused by wildfire smoke for different types of PV cells. This newly devised method can be adopted for power system operation and planning to ensure the stability and reliability of power grids. Additionally, this study highlights the need to consider different PV cell technologies in regions at high risk of wildfires to minimize the power reduction caused by wildfire smoke. 

This paper formulates a mixed integer linear programming (MILP) model to optimize a system of electric vehicle (EV) charging stations. Our methodology introduces a two-stage framework that integrates the first-stage system design problem with a second-stage control problem of the EV charging stations and develops a design and analysis of computer experiments (DACE) based system design optimization solution method. Our DACE approach generates a metamodel to predict revenue from the control problem using multivariate adaptive regression splines (MARS), fit over a binned Latin hypercube (LH) experimental design. Comparing the DACE based approach to using a commercial solver on the MILP, it yields near optimal solutions, provides interpretable profit functions, and significantly reduces computational time for practical application.