AMS Urban

project image

People

Michal Cap - Postdoctoral researcher
Prof. Javier Alonso-Mora

Funding

Amsterdam Institute for Advanced Metropolitan Solutions (AMS).

More Links
Github: multi-robot collision avoidance Github: MPCC implementation

About the Project

The use of automation is expected to revolutionise transportation of goods and people. Self-driving technology is being given increased attention as it can help provide personal point-to-point transportation that is affordable and leads to a reduction of parking capacity requirements. In addition to this, the focus must also be given to other forms of transportation like ships and improve the existing navigation methods for autonomous vessels. This would increase their reliability and ensure they can be increasingly used for transportation over water. This project focuses on both of these aspects by looking at fleet routing for self driving vehicles that provide ride sharing services. The other focus area is to develop a social trajectory planner for autonomous surface vessels.

Ridesharing has several advantages in modern day transportation systems. It can help reduce the number of vehicles required and also drastically reduce road traffic. This project models ridesharing using a fleet of self driving vehicles and aims to maximise service quality and minimise operation cost. This introduces a trade-off between these objectives and a scalable solution is introduced which can help service providers to make decisions about required fleet size and performance constraints.

This project also looks at waterways and introduces a trajectory planner for autonomous vessels which can help generate trajectories that resemble those of human-operated vessels. This can help these vessels learn socially compliant navigation behavior. This is essential when these have to operate in populated waterways with human-operated vessels as well. Unlike road vehicles, waterways do not have universal regulations or guidelines and thus are expected to operate in unstructured space. This is done by developing global trajectories for vessels and any deviation from nominal movements are penalized.

Project Demonstrations

Funding & Partners

This project is funded by the Amsterdam Institute for Advanced Metropolitan Solutions (AMS).

Social Trajectory Planning for Urban Autonomous Surface Vessels
S. Park, M. Cap, J. Alonso-Mora, C. Ratti, D. Rus. In , IEEE Transactions on Robotics (T-RO), 2020.

publisher pdf
In this article, we propose a trajectory planning algorithm that enables autonomous surface vessels to perform socially compliant navigation in a city's canal. The key idea behind the proposed algorithm is to adopt an optimal control formulation in which the deviation of movements of the autonomous vessel from nominal movements of human-operated vessels is penalized. Consequently, given a pair of origin and destination points, it finds vessel trajectories that resemble those of human-operated vessels. To formulate this, we adopt kernel density estimation (KDE) to build a nominal movement model of human-operated vessels from a prerecorded trajectory dataset, and use a Kullback-Leibler control cost to measure the deviation of the autonomous vessel's movements from the model. We establish an analogy between our trajectory planning approach and the maximum entropy inverse reinforcement learning (MaxEntIRL) approach to explain how our approach can learn the navigation behavior of human-operated vessels. On the other hand, we distinguish our approach from the MaxEntIRL approach in that it does not require well-defined bases, often referred to as features, to construct its cost function as required in many of inverse reinforcement learning approaches in the trajectory planning context. Through experiments using a dataset of vessel trajectories collected from the automatic identification system, we demonstrate that the trajectories generated by our approach resemble those of human-operated vessels and that using them for canal navigation is beneficial in reducing head-on encounters between vessels and improving navigation safety.

Multi-Objective Analysis of Ridesharing in Automated Mobility-on-Demand
M. Cap, J. Alonso-Mora. In Proc. Robotics: Science and Systems (RSS), 2018.

publisher pdf
Self-driving technology is expected to enable the realization of large-scale mobility-on-demand systems that employ massive ridesharing. The technology is being celebrated as a potential cure for urban congestion and others negative externalities of individual automobile transportation. In this paper, we quantify the potential of ridesharing with a fleet of autonomous vehicles by considering all possible trade-offs between the quality of service and operation cost of the system that can be achieved by sharing rides. We formulate a multi-objective fleet routing problem and present a solution technique that can compute Pareto-optimal fleet operation plans that achieve different trade- offs between the two objectives. Given a set of requests and a set of vehicles, our method can recover a trade-off curve that quantifies the potential of ridesharing with given fleet. We provide a formal optimality proof and demonstrate that the proposed method is scalable and able to compute such trade-off curves for instances with hundreds of vehicles and requests optimally. Such an analytical tool helps with systematic design of shared mobility system, in particular, it can be used to make principled decisions about the required fleet size.