Salvatore Candido
Papers
6
Total Citations
114
H-Index
5
About
Salvatore Candido is a roboticist whose work centers on planning and decision-making under uncertainty, with a particular focus on partially observable Markov decision processes (POMDPs). His most influential contribution is the development of minimum uncertainty navigation techniques for mobile robots, where he pioneered the use of information-guided POMDP planning to enable robots to safely reach goal configurations despite noisy sensors and unpredictable environments—a paper that has garnered 39 citations. Candido’s research also extends to humanoid robotics, where he improved hierarchical motion planners for bipedal locomotion in complex terrains, and to the integration of domain knowledge into POMDP-based systems to make planning more efficient and practical. His work on search problems with binary sensors and intrusion detection in remotely controlled systems further showcases his versatility. With over 100 total citations across his key publications, Candido has made a lasting impact on how robots reason about and act in uncertain, real-world settings.
Research Focus
Key Achievements
Top Papers
- 1Minimum uncertainty robot navigation using information-guided POMDP planning39 citations · 2011
- 2Minimum uncertainty robot path planning using a POMDP approach29 citations · 2010
- 3An improved hierarchical motion planner for humanoid robots25 citations · 2008
- 4
- 5
- 6Detecting intrusion faults in remotely controlled systems2 citations · 2009