Today, there are two major paradigms for vision-based autonomous driving systems: mediated perception approaches that parse an entire scene to make a driving decision, and behavior reflex approaches that directly map an input image to a driving action by a regressor. In this paper, we propose a third paradigm: a direct perception approach to estimate the affordance for driving. We propose to map an input image to a small number of key perception indicators that directly relate to the affordance of a road/traffic state for driving. Our representation provides a set of compact yet complete descriptions of the scene to enable a simple controller to drive autonomously. Falling in between the two extremes of mediated perception and behavior reflex, we argue that our direct perception representation provides the right level of abstraction. To demonstrate this, we train a deep Convolutional Neural Network using recording from 12 hours of human driving in a video game and show that our model can work well to drive a car in a very diverse set of virtual environments. We also train a model for car distance estimation on the KITTI dataset. Results show that our direct perception approach can generalize well to real driving images. Source code and data are available on our project website.

No abstract

This paper examines the chief findings of research conducted on policies to foster off-hour deliveries (OHDs) in the New York City metropolitan area. The goal was to estimate the overall impacts of eventual full implementation of an OHD program. As part of the research, a system of incentives was designed for the receivers of deliveries the system combined Global Positioning System (GPS) remote sensing monitoring with GPSenabled smart phones to induce a shift of deliveries to the off-hours from 7:00 p.m. to 6:00 a.m. The concept was pilot tested in Manhattan by 33 companies that switched delivery operations to the off-hours for a period of 1 month. At the in-depth interviews conducted after the test, the participants reported being very satisfied with the experience. As an alternative to road pricing schemes that target freight carriers, this was the first real-life trial of the use of financial incentives to delivery receivers. The analyses indicate that the economic benefits of a full implementation of the OHD program are in the range of $147 to $193 million per year, corresponding to savings on travel time and environmental pollution for regular-hour traffic as well as productivity increases for the freight industry. The pilot test also highlighted the great potential of unassisted OHDthat is, OHD made without personnel from the receiving establishment present-because almost all participants who used this modality decided to continue receiving OHD even after the financial incentive ended.

Over the past six decades, as private automobiles have become more affordable and more universal among American families, previously uncounted costs for cars have come to the forefront of the modern transportation debate, with some activists calling for an end to cars. This paper identifies five transit criteria that a transportation system must satisfy if it hopes to dethrone the individually owned and operated car as king of the road: (a) a solution to the congestion problem, (b) safety improvements over conventional manually operated cars, (c) lesser impact on the environment, (d) economic feasibility, and (e) comfort and convenience to rival the automobile. Given recent advancements in the field of vehicle autonomy, a potential solution to the car's growing problems has presented itself: an autonomous taxi network (ATN). Drawing from the classic personal rapid transit model as well as Mark Gorton's idea of smart paratransit, two potential designs for an ATN are presented and compared with one another, and the viability of the ATN concept is explored in view of statewide transportation demand in New Jersey. With travel demand as generated by Talal Mufti in 2012, the smart paratransit model emerges as the more economically viable implementation, requiring a fleet size between 1.6 and 2.8 million six-passenger vehicles to meet the state's travel demand in its entirety, at a cost to consumers of $16.30 to $23.50 per person per day.

This study has done an empirical analysis of long-haul truck drivers’ route choice decision making as they navigate the U.S. highway network. The most important factor that has been analyzed is how long-haul truck drivers trade off between distance and time when faced with multiple routes. From information gathered from a revealed preference data set consisting of about 250,000 trucks over a 13-day period, a logistic model was constructed to describe route choice behavior when truck drivers are faced with alternate routes. The logistic model predicted the percentage of trucks that used the bypass route as a function of the perceived speed on the downtown route. The results of this study show that time is a significant factor in the decision-making process.

Data were analyzed from 74 "Freight Mobility Interviews"-surveys conducted with key transportation executives whose products and services are shipped into New York City's central business district (CBD). Quantitative data collected included company profiles, defined by product category; kind of transportation service; type of distribution channel; characteristics of dispatched truck trip; and time and cost for last leg of trip. Major barriers to freight mobility identified by logistics/distribution/ transportation managers were widespread congestion, theft/vandalism, inadequate docking space, and insufficient curbside parking for commercial vehicles. Recommendations to increase productivity in the CBD included off-peak and extended delivery hours, additional truck parking zones, and incentives to upgrade docking areas. Barriers to freight mobility were consistent across industry sectors. Initiatives that have the potential to increase the efficiency of urban goods movement include improved law enforcement to deter theft/vandalism, information-based improvements such as accurate signage, the use of ITS technology and management systems to actively manage curbside commercial parking zones, and improved road maintenance. The nontraditional methodology developed for collecting urban freight mobility data provides process-oriented data that reflect changing supply chain strategies of private-sector shippers and carriers.Urban congestion continues to grow in metropolitan areas throughout the United States and worldwide (1). Changing distribution and transportation strategies enabled by freight carrier deregulation and supply chain management practices, such as just-in-time and continuous replenishment, are factors that may have contributed to more frequent deliveries. Having more trucks on the streets leads to more congestion in urban areas. However, in the New York metropolitan area, a mature infrastructure and a shrinking public economy do not support traditional "demolition, bricks, and mortar" solutions. A lack of qualitative and quantitative performance and cost data has hindered urban planners in responding to evolving transportation patterns. Transportation planners require state-of-the-art data on freight mobility to develop innovative management approaches to relieving congestion. Access to process-oriented freight mobility data, reflecting business decisions, would facilitate an active management approach that could use information technology to develop strategically focused transportation solutions.

No abstract

No abstract