Aniruddh G. Puranic

Aniruddh G. Puranic

Auto-generated profile, based on publicly available information

Aniruddh G. Puranic

Computer Science Department, University of Southern California, Los Angeles, CA, USA

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
25 June 2021 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
APAniruddh G. Puranic
Aniruddh G. Puranic
JDJyotirmoy V. Deshmukh
Jyotirmoy V. Deshmukh
SNStefanos Nikolaidis
Stefanos Nikolaidis
Learning control policies that are safe, robust and interpretable are prominent challenges in developing robotic systems. Learning-from-demonstrations with formal logic is an arising paradigm in reinforcement learning to estimate rewards and extract robot control policies that seek to overcome these challenges. In this approach, we assume that mission-level specifications for the robotic system are expressed in a suitable temporal logic such as Signal Temporal Logic (STL). The main idea is to automatically infer rewards from user demonstrations (that could be suboptimal or incomplete) by evaluating and ranking them w.r.t. the given STL specifications. In contrast to existing work that focuses on deterministic environments and discrete state spaces, in this letter, we propose significant extensions that tackle stochastic environments and continuous state spaces.

22 April 2020
Verified
Conference Paper
Open access
SMSara Mohammadinejad
Sara Mohammadinejad
JDJyotirmoy V. Deshmukh
Jyotirmoy V. Deshmukh
APAniruddh G. Puranic
Aniruddh G. Puranic
MVMarcell Vazquez-Chanlatte
Marcell Vazquez-Chanlatte
ADAlexandre Donzé
Alexandre Donzé
Cyber-physical system applications such as autonomous vehicles, wearable devices, and avionic systems generate a large volume of time-series data. Designers often look for tools to help classify and categorize the data. Traditional machine learning techniques for time-series data offer several solutions to solve these problems; however, the artifacts trained by these algorithms often lack interpretability. On the other hand, temporal logic, such as Signal Temporal Logic (STL) have been successfully used in the formal methods community as specifications of time-series behaviors. In this work, we propose a new technique to automatically learn temporal logic formulas that are able to classify real-valued time-series data. Previous work on learning STL formulas from data either assumes a formula-template to be given by the user, or assumes some special fragment of STL that enables exploring the formula structure in a systematic fashion. In our technique, we relax these assumptions, and provide a way to systematically explore the space of all STL formulas. As the space of all STL formulas is very large, and contains many semantically equivalent formulas, we suggest a technique to heuristically prune the space of formulas considered. Finally, we illustrate our technique on various case studies from the automotive and transportation domains.

15 January 2016 in International Journal of Computer Applications
Verified
Journal Article
Closed access
APAniruddh Puranic
Aniruddh Puranic
DKDeepak K.
Deepak K.
UVUmadevi V.
Umadevi V.

1 March 2019
Verified
Conference Paper
Closed access
ABAnand Balakrishnan
Anand Balakrishnan
APAniruddh G. Puranic
Aniruddh G. Puranic
XQXin Qin
Xin Qin
ADAdel Dokhanchi
Adel Dokhanchi
JDJyotirmoy V. Deshmukh
Jyotirmoy V. Deshmukh
GFGeorgios Fainekos
Georgios Fainekos

1 April 2020
Verified
Conference Paper
Closed access
SMSara Mohammadinejad
Sara Mohammadinejad
JDJyotirmoy V. Deshmukh
Jyotirmoy V. Deshmukh
APAniruddh G. Puranic
Aniruddh G. Puranic
Many complex cyber-physical systems can be modeled as heterogeneous components interacting with each other in real-time. We assume that the correctness of each component can be specified as a requirement satisfied by the output signals produced by the component, and that such an output guarantee is expressed in a real-time temporal logic such as Signal Temporal Logic (STL). In this paper, we hypothesize that a large subset of input signals for which the corresponding output signals satisfy the output requirement can also be compactly described using an STL formula that we call the environment assumption. We propose an algorithm to mine such an environment assumption using a supervised learning technique. Essentially, our algorithm treats the environment assumption as a classifier that labels input signals as good if the corresponding output signal satisfies the output requirement, and as bad otherwise. Our learning method simultaneously learns the structure of the STL formula as well as the values of the numeric constants appearing in the formula. 1 To achieve this, we combine a procedure to systematically enumerate candidate Parametric STL (PSTL) formulas, with a decision-tree based approach to learn parameter values. We demonstrate experimental results on real world data from several domains including transportation and health care.

1 December 2022 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
APAniruddh G. Puranic
Aniruddh G. Puranic
JDJyotirmoy V. Deshmukh
Jyotirmoy V. Deshmukh
SNStefanos Nikolaidis
Stefanos Nikolaidis
In the paradigm of robot learning-from-demonstra tions (LfD), understanding and evaluating the demonstrated behaviors plays a critical role in extracting control policies for robots. Without this knowledge, a robot may infer incorrect reward functions that lead to undesirable or unsafe control policies. Prior work has used temporal logic specifications, manually ranked by human experts based on their importance, to learn reward functions from imperfect/suboptimal demonstrations. To overcome reliance on expert rankings, we propose a novel algorithm that learns from demonstrations, a partial ordering of provided specifications in the form of a performance graph. Through various experiments, including simulation of industrial mobile robots, we show that extracting reward functions with the learned graph results in robot policies similar to those generated with the manually specified orderings. We also show in a user study that the learned orderings match the orderings or rankings by participants for demonstrations in a simulated driving domain. These results show that we can accurately evaluate demonstrations with respect to provided task specifications from a small set of imperfect data with minimal expert input.