PhD: Mobile manipulation in dynamic environments

Updated: 2 months ago
Deadline: 16 Jun 2019

PhD1: Mobile manipulation in dynamic environments
In the future warehouses and stores, mobile manipulators will perform complex tasks in environments shared with humans. Traditionally task scheduling and manipulation have been decoupled from motion planning. Yet, when robots navigate in critical and dynamic environments, plans may have to be adapted online to take into account congestion, interaction with other robots and human co-workers/customers and interaction with the objects being manipulated. You will devise methods for motion planning that schedule plans for the robots and adapt them online taking into account the priority of tasks, their associated uncertainty and the preferences and needs of human co-workers or customers (e.g., the robot may push a trolley to the side to let a customer pass or modify its position to continue performing its task without causing any inconvenience to the customer). The goal is to have an integrated approach for motion planning in uncertain and dynamic environments, which accounts for complex manipulation, navigation and coordination tasks, and that provides performance guarantees (in expectation).

Research Approach:

  • Global planning: Sampling-based path planning with guarantees
  • Local planning and manipulation: Real-time nonlinear constrained optimization
  • Machine learning for models of human/customer behavior
  • Learning preferences/cost function for areas to traverse

This PhD position is part of a larger research effort to study AI and Robotics for retail (supermarkets, distribution centres, online retail and supply chain) at the Delft University of Technology, see ). Together with Ahold Delhaize -a multinational retail organization with brands such as Albert Heijn, Delhaize,, Etos, Gall&Gall, Stop & Shop- and the Dutch Innovation Center for AI, the TUDelft, has started a joint research lab to join the best of academic and industrial research. The lab focuses on fundamental research in artificial intelligence and robotics for retail. The lab will host 5 PhD positions and research assistants. It is led by Prof. Martijn Wisse, and has principal investigators per domain. One of the perks this industry collaboration program is the possibility for scientists to conduct both foundational research and test or pilot ideas in an applied context.
In Delft, we currently have three vacant PhD positions, namely:

  • PhD1: Mobile manipulation in dynamic environments
  • PhD2: Self-adaptive robot architectures for reliable, safe and explainable autonomous behaviour
  • PhD3: Predictive Vehicle Routing for On-demand Logistics

If you are interested in multiple positions, please apply only to the one that interests you the most and mention in your motivation letter your interest in multiple positions. You will be automatically considered for those positions.

View or Apply

Similar Positions