D.J. Austin

About

D.J. Austin is a leading researcher in mobile robotics, with a primary focus on probabilistic localization and state estimation. His most influential work centers on advancing the CONDENSATION algorithm for feature-based global localization in large-scale environments. Austin’s major contributions include demonstrating how CONDENSATION with planned sampling can represent uncertainty in robot pose, effectively achieving a breakthrough in this domain. He also pioneered the use of multiple Gaussian hypotheses to model probability distributions, offering a computationally efficient alternative to large sample sets. His key papers on these topics have garnered over 180 citations combined, reflecting their lasting impact on the field. Beyond localization, Austin has explored geometric constraint mapping and hybrid dynamic control for robotic assembly and mobile manipulation, showing versatility in both perception and control. His work is essential reading for students and researchers tackling real-world robot navigation under uncertainty.

Research Focus

Key Achievements

Top Papers

1. 1
   Feature based CONDENSATION for mobile robot localization

   70 citations · 2002
2. 2
   Experiments on augmenting CONDENSATION for mobile robot localization

   64 citations · 2002
3. 3
   Using multiple Gaussian hypotheses to represent probability distributions for mobile robot localization

   53 citations · 2002
4. 4
   Geometric constraint identification and mapping for mobile robots

   21 citations · 2001
5. 5
   Model-Adaptive Hybrid Dynamic Control for Robotic Assembly Tasks

   5 citations · 1999
6. 6
   Simultaneous identification and control of a hybrid dynamic model for a mobile robot

   2 citations · 2002

Key Collaborators

Contact & Links