Richard Dearden

About

Richard Dearden is a leading researcher in robot task planning and decision-making under uncertainty, with a focus on enabling autonomous systems to operate reliably in open and unpredictable environments. His major contributions lie at the intersection of probabilistic state estimation, hierarchical planning, and explainable AI for robotics. Dearden’s most influential work, "Robot task planning and explanation in open and uncertain worlds" (152 citations), advances the ability of robots to both plan and justify their actions in real-time. His landmark 2004 paper "Diagnosis by a Waiter and a Mars Explorer" (102 citations) pioneered the use of particle filters combined with classical algorithms for efficient real-time diagnosis in mobile robots, a technique that has been widely adopted. Dearden also developed hierarchical POMDP-based approaches for planning visual actions (e.g., "Planning to see," 53 citations) and information-lookahead strategies for autonomous underwater vehicle mapping. His work on exploiting probabilistic knowledge and commonsense reasoning (46 citations) has been instrumental in creating robots that balance efficiency with robustness. With over 450 total citations, Dearden’s research continues to shape how robots perceive, plan, and explain their behavior in complex, uncertain worlds.

Research Focus

Key Achievements

Top Papers

1. 1
   Robot task planning and explanation in open and uncertain worlds

   152 citations · 2015
2. 2
   Diagnosis by a Waiter and a Mars Explorer

   102 citations · 2004
3. 3
   Planning to see: A hierarchical approach to planning visual actions on a robot using POMDPs

   53 citations · 2010
4. 4
   Exploiting Probabilistic Knowledge under Uncertain Sensing for Efficient Robot Behaviour

   46 citations · 2011
5. 5
   A Switching Planner for Combined Task and Observation Planning

   33 citations · 2011
6. 6
   HiPPo: hierarchical POMDPs for planning information processing and sensing actions on a robot

   33 citations · 2008
7. 7
   Manipulation planning using learned symbolic state abstractions

   27 citations · 2013
8. 8
   Architecture and Representations

   14 citations · 2010
9. 9
   Information-lookahead planning for AUV mapping

   10 citations · 2009
10. 10
    Navigation Planning in Probabilistic Roadmaps with Uncertainty

    10 citations · 2009

Key Collaborators

Contact & Links