A
Aniruddh G. Puranic
Researcher at University of Southern California
Publications - 11
Citations - 131
Aniruddh G. Puranic is an academic researcher from University of Southern California. The author has contributed to research in topics: Temporal logic & Interpretability. The author has an hindex of 4, co-authored 9 publications receiving 62 citations. Previous affiliations of Aniruddh G. Puranic include Toyota Motor Engineering & Manufacturing North America.
Papers
More filters
Journal ArticleDOI
Vehicle Number Plate Recognition System: A Literature Review and Implementation using Template Matching
TL;DR: This paper attempts to review the various techniques and their usage of the Automatic Number Plate Recognition System (ANPR) in India and finds its accuracy was found to be 80.8% for Indian number plates.
Proceedings ArticleDOI
Specifying and Evaluating Quality Metrics for Vision-based Perception Systems
Anand Balakrishnan,Aniruddh G. Puranic,Xin Qin,Adel Dokhanchi,Jyotirmoy V. Deshmukh,Heni Ben Amor,Georgios Fainekos +6 more
TL;DR: It is shown how TQTL can be a useful tool to determine quality of perception, and offers an alternative metric that can give useful information, even in the absence of ground truth labels.
Journal ArticleDOI
Learning From Demonstrations Using Signal Temporal Logic in Stochastic and Continuous Domains
TL;DR: In this paper, the authors propose a reinforcement learning approach to estimate rewards from user demonstrations by evaluating and ranking them w.r.t. the given signal temporal logic (STL) specifications.
Posted Content
Interpretable Classification of Time-Series Data using Efficient Enumerative Techniques
Sara Mohammadinejad,Jyotirmoy V. Deshmukh,Aniruddh G. Puranic,Marcell Vazquez-Chanlatte,Alexandre Donzé +4 more
TL;DR: This work proposes a new technique to automatically learn temporal logic formulas that are able to classify real-valued time-series data and suggests a technique to heuristically prune the space of formulas considered.
Proceedings ArticleDOI
Interpretable classification of time-series data using efficient enumerative techniques
Sara Mohammadinejad,Jyotirmoy V. Deshmukh,Aniruddh G. Puranic,Marcell Vazquez-Chanlatte,Alexandre Donzé +4 more
TL;DR: In this article, the authors propose a technique to automatically learn temporal logic formulas that are able to classify real-valued time-series data, and demonstrate their technique on various case studies from the automotive and transportation domains.