Nils Wilde

Postdoctoral Fellow at TU Delft

Short Bio:

I am currently a Postdoctoral Fellow in the Autonomous Multi-Robots Lab working with Javier Alonso-Mora at TU Delft. Until August 2021 I was a postdoctoral fellow at the Autonomous Systems Lab at the University of Waterloo where I also did my PhD in Electrical and Computer Engineering (ECE) under the co-supervision of Dana Kulić and Stephen L. Smith from 2016 to 2020. Before that I completed my BSc. and MSc. degrees at the Technical University Berlin in 2012 and 2016, respectively.

My research focuses on human-robot / human-AI interaction, preference learning, learning from human feedback, multi-robot coordination and task assignment, vehicle routing, motion planning and multi-objective planning. Please find details about recent research projects under Research.

News:

February 2024 Our work on Regret-based Sampling of Pareto Fronts for Multi-Objective Robot Planning Problems was accepted at Transactions on Robotics (T-RO)! The full paper is available here.
January 2024 New year, new paper: Our work on Scalarizing Multi-Objective Robot Planning Problems using Weighted Maximization was accepted at RA-L, the preprint is available on arXiv.
December 2023 We received a nice Christmas letter publication decision that our paper Statistically Distinct Plans for Multi-Objective Planning and Task Assignment was accepted at Transactions on Robotics (T-RO)! The preprint is available on arXiv.
October 2023 We had a great day running our Workshop on Human Multi-Robot Interaction at IROS 2023. Thanks to all who contributed and attended!
September 2023 Our paper Designing Heterogeneous Robot Fleets for Task Allocation and Sequencing was accepted at the International Symposium on Multi-Robot and Multi-Agent Systems (MRS)! [pdf]
August 2023 We have extended the deadline for contributions to our workshop on Human Multi-Robot Interaction at IROS 2023 until September 1st. See our website for more details.
July 2023 Our paper A Unified Approach to Optimally Solving Sensor Scheduling and Sensor Selection Problems in Kalman Filtering was accepted at CDC 2023 IEEE Conference on Decision and Control (CDC) 2023, congrats to first author Shamak!
July 2023 Our paper Optimizing Task Waiting Times in Dynamic Vehicle Routing was accepted at RA-L! [arXiv]
April 2023 Our workshop on "Human Multi-Robot Interaction" was accepted at IROS 2023. More announcements to follow soon!
UPDATE: We are pleased to invite submissions of short papers (4 pages) to our workshop. The full call for papers and submission instructions can be found on the workshop's website.
January 2023 Our paper Approximation Algorithms for Robot Tours in Random Fields with Guaranteed Estimation Accuracy was accepted at ICRA 2023, congratulations to first author Shamak Dutta!
December 2022 The Canadian Robotics Network NCRN invited me to give a seminar at McGill University in Montreal, thanks to everyone involved for a spectacular visit!
November 2022 I gave invited talks at the Robotics and Biology Lab at TU Berlin as well as at Kavraki Lab at Rice University, thanks for the kind invitations!
September 2022 Our paper Do we use the Right Measure? Challenges in Evaluating Reward Learning Algorithms was accepted at the Conference on Robot Learning (CoRL)!
July 2022 Our paper Online Multi-Robot Task Assignment with Stochastic Blockages was accepted at the IEEE Conference on Decision and Control (CDC) 2022!
Moreover, I am co-author of two other papers, Scheduling Operator Assistance for Shared Autonomy in Multi-Robot Teams and Informative Path Planning in Random Fields via Mixed Integer Programming, which both also got accepted at CDC, congrats to first authors Yifan and Shamak!
May 2022 Our paper Learning Submodular Objectives for Team Environmental Monitoring will be featured in the Workshop on Robotics for Climate Change at ICRA 2022.
March 2022: Our paper Error-Bounded Approximation of Pareto Fronts in Robot Planning Problems, was accepted at WAFR 2022!
November 2021: New journal paper Learning Submodular Objectives for Team Environmental Monitoring, accepted at RA-L, with presentation at ICRA 2022.
September 2021: I started a new Postdoc at TU Delft, working together with Prof. Javier Alonso-Mora! Thanks Waterloo and Canada for all the fantastic times, great research endeavours with Stephen Smith, Dana Kulic and all the great people in their labs. Until next time, Canada!
September 2021: Our paper Learning Reward Functions from Scale Feedback , was accepted at CoRL 2021.
September 2020: I successfully defended my PhD thesis on September 2nd. A huge thanks goes to my supervisors Dana Kulic and Stephen L. Smith as well as to my committee members Anca Dragan, Christopher Nielsen, David Wang and Steve Waslander! The pdf of my thesis is available from the UW library.
July 2020: Our paper Active Preference Learning using Maximum Regret, was accepted at IROS 2020.
April 2020: Our journal paper Improving User Specifications for Robot Behavior through Active Preference Learning: Framework and Evaluation, will be presented at the Workshop on Interactive Robot Learning (WIRL) at ICRA 2020.
April 2020: Our paper Learning Control Sets for Lattice Planners from User Preferences, first authored by Alexander Botros and me, was accepted at WAFR 2020.
January 2020: Our paper Learning User Preferences from Corrections on State Lattices was accepted at ICRA 2020.

Contact

Department for Cognitive Robotics (CoR), 3ME, TU Delft

Building 34, Mekelweg 2,2628 CD Delft

email: n.wilde@tudelft.nl