published journal article
conference paper
This paper proposes a new algorithm to solve the Multi-period Continuous Network Design Problem (MPCNDP) in a real options framework. The MPCNDP aims to find the long-term optimal highway expansion plan for a road network with stochastic demand. Analytical methods, finite difference methods or Least Square Monte Carlo simulation (LSMC) are not applicable for solving the MPCNDP because of the high dimension of the stochastic demand variables and the complexity of the intrinsic complexity of the network design problem. The authors propose an algorithm, which they call â??Approximate Least Square Monte Carlo simulationâ?? (ALSMC). This algorithm applies least square regression to estimate the value of the termination payoff function without knowing the optimal capacity improvement plan. During each iteration, only a multi-period CNDP with deterministic demand needs to be solved, which dramatically reduces the computing time of each termination payoff function. The authors first test the ALSMC method on a simple example for which the exact solution is known, and show that it converges quickly to the solution. They then test the ALSMC method on a small network with 6 centroids and 16 links, which has been used as a benchmark in dozens of papers. The authors find that the ALSMC method gives quick and reasonably accurate estimates of the termination payoff function.
published journal article
conference paper
published journal article
This paper presents a case study examining emissions impacts of a modal shift from on-road trucks to rail for goods movement through the Southern California ports region, one of the severest nonattainment areas in terms of national air quality standards. Recent completion of the Alameda Corridor, a 20-mile rail expressway connecting the Ports of Long Beach and Los Angeles with rail main lines near downtown Los Angeles, provides substantial reserve capacity for port traffic to be diverted from the severely congested road network to the rail line. On-road vehicle emissions were estimated using California’s mobile-source emissions model EMFAC that incorporates a set of emissions factors for each vehicle type and an estimate of vehicle activity. These emissions were then compared with the emissions generated from trains increased to carry freight volume diverted from truck traffic. On the basis of year 2000 traffic level, it was estimated that for a 20% modal shift of port traffic, mobile-source emissions can be reduced up to 0.86 tons for nitrogen oxides and 16 kg for particulates/day. The analysis results indicate encouraging the modal shift for port-related freight traffic should be an integral part of overall air quality improvement initiatives for the study area.
published journal article
There is considerable evidence that evaluating the subjective risk level of driving decisions can improve the safety of Autonomous Driving Systems (ADS) in both typical and complex driving scenarios. In this paper, we propose a novel data-driven approach that uses scene-graphs as intermediate representations for modeling the subjective risk of driving maneuvers. Our approach includes a Multi-Relation Graph Convolution Network, a Long-Short Term Memory Network, and attention layers. To train our model, we formulate subjective risk assessment as a supervised scene classification problem. We evaluate our model on both synthetic lane-changing datasets and real-driving datasets with various driving maneuvers. We show that our approach achieves a higher classification accuracy than the state-of-the-art approach on both large (96.4% vs. 91.2%) and small (91.8% vs. 71.2%) lane-changing synthesized datasets, illustrating that our approach can learn effectively even from small datasets. We also show that our model trained on a lane-changing synthesized dataset achieves an average accuracy of 87.8% when tested on a real-driving lane-changing dataset. In comparison, the state-of-the-art model trained on the same synthesized dataset only achieved 70.3% accuracy when tested on the real-driving dataset, showing that our approach can transfer knowledge more effectively. Moreover, we demonstrate that the addition of spatial and temporal attention layers improves our model’s performance and explainability. Finally, our results illustrate that our model can assess the risk of various driving maneuvers more accurately than the state-of-the-art model (86.5% vs. 58.4%, respectively).
published journal article
published journal article
We consider the problem of collectively transporting multiple objects using air–ground multirobot teams. The objective is to find the optimal matching between the objects and aerial/ground robots that minimizes the energy of the overall system. We reveal the local optimality criteria for this combinatorial problem and prove that combining a branch and bound algorithm with a negative-cycle canceling algorithm (NCCA) yields an efficient algorithm that provides the globally optimal solution of the problem. Numerical experiments demonstrate the performance on practical problems.
policy brief
Workers in Southern California currently face transportationrelated challenges accessing employment opportunities, including but not limited to high parking costs and/or limited parking availability in dense employment and residential areas; long commute distances between residential areas and employment opportunities; and poor transit service quality in many areas. These challenges are particularly burdensome for low-income households that may not have access to a personal vehicle and/or live in jobpoor neighborhoods, as having a personal vehicle may be the only viable way to get to work.
conference paper