J
Javier Alonso-Mora
Researcher at Delft University of Technology
Publications - 148
Citations - 5718
Javier Alonso-Mora is an academic researcher from Delft University of Technology. The author has contributed to research in topics: Computer science & Motion planning. The author has an hindex of 31, co-authored 103 publications receiving 3609 citations. Previous affiliations of Javier Alonso-Mora include ETH Zurich & Institute of Robotics and Intelligent Systems.
Papers
More filters
Proceedings ArticleDOI
Human - robot swarm interaction for entertainment: from animation display to gesture based control
TL;DR: Experimental results with three systems that take real-time user input to direct a robot swarm formed by tens of small robots are shown, including real- time drawing, gesture based interaction with an RGB-D sensor and control via a hand-held tablet computer.
Journal ArticleDOI
Scenario-Based Trajectory Optimization in Uncertain Dynamic Environments
TL;DR: In this article, an optimization-based method to plan the motion of an autonomous robot under the uncertainties associated with dynamic obstacles, such as humans, is presented, which bounds the marginal risk of collisions by incorporating chance constraints into the planning problem.
Proceedings ArticleDOI
Optimizing Vehicle Distributions and Fleet Sizes for Shared Mobility-on-Demand
TL;DR: This paper presents an offline method to optimize the vehicle distributions and fleet sizes on historical demand data for MoD systems that allow passengers to share vehicles and presents an algorithm to determine how many vehicles are needed, where they should be initialized, and how theyShould be routed to service all the travel demand for a given period of time.
Patent
On-Demand High-Capacity Ride-Sharing Via Dynamic Trip-Vehicle Assignment with Future Requests
TL;DR: In this paper, a method and system for vehicle routing and request assignment which incorporates a prediction of future demand is described, which seamlessly integrates sampled future requests into request assignments and vehicle routing.
Posted Content
Social-VRNN: One-Shot Multi-modal Trajectory Prediction for Interacting Pedestrians.
TL;DR: This paper presents a variational learning approach for interaction-aware and multi-modal trajectory prediction based on deep generative neural networks that can achieve faster convergence and requires significantly fewer samples comparing to state-of-the-art methods.