Research Team: PI: Chee Wei Wong Team:
About this project:
Recently UCLA has been developing state-of-the-art chip-scale LiDAR sensors for autonomous self-driving vehicles and improved driving safety. The chip-scale LiDAR sensors, with our high-performance precision laser characteristics enable next-generation transportation density mapping across the metropolitan Los Angeles. In this project, the researchers will use the LiDAR sensor to map out real-time multimodal traffic and network characteristics in multiple road links and intersections in the UCLA-Westwood area. Our chip-scale state-of-the-art lasers developed at UCLA serve as the impetus for wide-spread LiDAR implementation. By understanding the Westwood traffic characteristics in finer precision and in real-time along the high-density corridors, we provide previously unavailable inputs to the SCAG transportation planning model and to the intelligent traffic optimization of the Westwood area. To evaluate this project, we will compare the LiDAR datasets obtained versus prior data used by SCAG, estimate the potential benefits of the new generation of scalable LiDAR precision mapping to SCAG’s regional transportation model, and evaluate the potential of low-cost LiDAR inputs into the metropolitan transportation planning process.
What problem does this research aim to address?
Metropolitan areas across the world use travel demand models and expensive data collected from various labor-intensive sources to forecast road traffic in order to assist decision making on regional transportation system operation, infrastructure investment, environmental protection and land use planning. The validation of traffic assignment is one of the most crucial steps in the metropolitan transportation modeling process. The ability of the
model to produce base year volume estimates within acceptable ranges of tolerance compared to actual ground counts is essential to validate the entire travel demand model. However,metropolitan transportation demand models rely primarily on expensive and infrequent household door-to-door surveys and limited observed data from sensors (mainly inductive loops and traffic cameras, sometimes sensors on vehicles). Other GPS-based data such as mobile phones and Google maps only provide coarse and/or fragmented data due to decentralized collection and data ownership, often extremely high data processing cost, and inadequate precision on how a subset of travelers and vehicles move around in the city.
Moreover, the currently available data is rather inadequate in providing observations on the vehicle type, non-vehicle traffic, and vehicular occupancy. Such deficiencies are critical barriers to further improvement of the transportation demand model as multimodal mixed traffic and high-occupancy vehicles (HOV) are increasingly more important in planning metropolitan LA.
What are the expected impacts and benefits of the research?
SCAG is developing the next generation of urban transportation demand models that are aimed at producing more accurate, “big” data for multimodal transportation system users. The proposed research explores providing previously unavailable data at a low cost. If scalable, this would greatly assist SCAG in acquiring big data for future transportation demand models.