V
Vandi Verma
Researcher at California Institute of Technology
Publications - 38
Citations - 1549
Vandi Verma is an academic researcher from California Institute of Technology. The author has contributed to research in topics: Particle filter & Fault (power engineering). The author has an hindex of 16, co-authored 31 publications receiving 1430 citations. Previous affiliations of Vandi Verma include Jet Propulsion Laboratory & Carnegie Mellon University.
Papers
More filters
Proceedings ArticleDOI
Experiences with a mobile robotic guide for the elderly
TL;DR: An implemented robot system, which relies heavily on probabilistic AI techniques for acting under uncertainty, and successfully demonstrated that it could autonomously provide guidance for elderly residents in an assisted living facility.
Proceedings ArticleDOI
Recent progress in local and global traversability for planetary rovers
TL;DR: This paper reports on the extension on the systems that were previously developed that were necessary to achieve autonomous navigation in this domain and the algorithms have been tested on the outdoor prototype rover, Bullwinkle, and have recently driven 100 m at a speed of 15 cm/sec.
Journal ArticleDOI
Real-time fault diagnosis [robot fault diagnosis]
TL;DR: In this paper, the authors present a number of complementary algorithms for detecting faults on-board operating robots, where a fault is defined as a deviation from expected behavior, and the algorithms focus on faults that cannot directly be detected from current sensor values but require inference from a sequence of timevarying sensor values.
Journal ArticleDOI
AEGIS autonomous targeting for ChemCam on Mars Science Laboratory: Deployment and results of initial science team use.
R. Francis,Tara Estlin,Gary Doran,S. Johnstone,Daniel Gaines,Vandi Verma,Michael C. Burl,Jens Frydenvang,Suzanne Montaño,Roger C. Wiens,Steven R. Schaffer,Olivier Gasnault,Lauren DeFlores,Diana L. Blaney,Benjamin Bornstein +14 more
TL;DR: Performance in autonomously selecting the most desired target material over the last 2.5 kilometers of driving into previously unexplored terrain exceeds 93% (where ~24% is expected without intelligent targeting), and all observations resulted in a successful geochemical observation.
Proceedings Article
Risk Sensitive Particle Filters
TL;DR: By incorporating a cost model into particle filtering, states that are more critical to the system performance are more likely to be tracked.