39 citations · 64 across the 19 of their papers we have counts for
23 papers
Automata-Conditioned Cooperative Multi-Agent Reinforcement Learning
Beyazit Yalcinkaya, Marcell Vazquez-Chanlatte, Ameesh Shah +2
We study learning multi-task, multi-agent policies for cooperative, temporal objectives, under centralized training, decentralized execution. In this setting, using automata to rep…
Using Language and Road Manuals to Inform Map Reconstruction for Autonomous Driving
Akshar Tumu, Henrik I. Christensen, Marcell Vazquez-Chanlatte +2
Lane-topology prediction is a critical component of safe and reliable autonomous navigation. An accurate understanding of the road environment aids this task. We observe that this…
FALCON: Learning Force-Adaptive Humanoid Loco-Manipulation
Yuanhang Zhang, Yifu Yuan, Prajwal Gurunath +7
Humanoid loco-manipulation holds transformative potential for daily service and industrial tasks, yet achieving precise, robust whole-body control with 3D end-effector force intera…
Provably Correct Automata Embeddings for Optimal Automata-Conditioned Reinforcement Learning
Beyazit Yalcinkaya, Niklas Lauffer, Marcell Vazquez-Chanlatte +1
Automata-conditioned reinforcement learning (RL) has given promising results for learning multi-task policies capable of performing temporally extended objectives given at runtime,…
SD++: Enhancing Standard Definition Maps by Incorporating Road Knowledge using LLMs
Hitvarth Diwanji, Jing-Yan Liao, Akshar Tumu +3
High-definition maps (HD maps) are detailed and informative maps capturing lane centerlines and road elements. Although very useful for autonomous driving, HD maps are costly to bu…
Compositional Automata Embeddings for Goal-Conditioned Reinforcement Learning
Beyazit Yalcinkaya, Niklas Lauffer, Marcell Vazquez-Chanlatte +1
Goal-conditioned reinforcement learning is a powerful way to control an AI agent's behavior at runtime. That said, popular goal representations, e.g., target states or natural lang…
Diffusion-Based Failure Sampling for Evaluating Safety-Critical Autonomous Systems
Harrison Delecki, Marc R. Schlichting, Mansur Arief +3
Validating safety-critical autonomous systems in high-dimensional domains such as robotics presents a significant challenge. Existing black-box approaches based on Markov chain Mon…
ScenicNL: Generating Probabilistic Scenario Programs from Natural Language
Karim Elmaaroufi, Devan Shanker, Ana Cismaru +4
For cyber-physical systems (CPS), including robotics and autonomous vehicles, mass deployment has been hindered by fatal errors that occur when operating in rare events. To replica…
Entropy-regularized Point-based Value Iteration
Harrison Delecki, Marcell Vazquez-Chanlatte, Esen Yel +4
Model-based planners for partially observable problems must accommodate both model uncertainty during planning and goal uncertainty during objective inference. However, model-based…
: Learning Automata from Examples using Natural Language Oracles
Marcell Vazquez-Chanlatte, Karim Elmaaroufi, Stefan J. Witwicki +2
Expert demonstrations have proven an easy way to indirectly specify complex tasks. Recent algorithms even support extracting unambiguous formal specifications, e.g. deterministic f…
Learning Formal Specifications from Membership and Preference Queries
Ameesh Shah, Marcell Vazquez-Chanlatte, Sebastian Junges +1
Active learning is a well-studied approach to learning formal specifications, such as automata. In this work, we extend active specification learning by proposing a novel framework…
Learning Deterministic Finite Automata Decompositions from Examples and Demonstrations
Niklas Lauffer, Beyazit Yalcinkaya, Marcell Vazquez-Chanlatte +2
The identification of a deterministic finite automaton (DFA) from labeled examples is a well-studied problem in the literature; however, prior work focuses on the identification of…
Demonstration Informed Specification Search
Marcell Vazquez-Chanlatte, Ameesh Shah, Gil Lederman +1
This paper considers the problem of learning temporal task specifications, e.g. automata and temporal logic, from expert demonstrations. Task specifications are a class of sparse m…
Model Checking Finite-Horizon Markov Chains with Probabilistic Inference
Steven Holtzen, Sebastian Junges, Marcell Vazquez-Chanlatte +3
We revisit the symbolic verification of Markov chains with respect to finite horizon reachability properties. The prevalent approach iteratively computes step-bounded state reachab…
Entropy-Guided Control Improvisation
Marcell Vazquez-Chanlatte, Sebastian Junges, Daniel J. Fremont +1
High level declarative constraints provide a powerful (and popular) way to define and construct control policies; however, most synthesis algorithms do not support specifying the d…
Interpretable Classification of Time-Series Data using Efficient Enumerative Techniques
Sara Mohammadinejad, Jyotirmoy V. Deshmukh, Aniruddh G. Puranic +2
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…
Maximum Causal Entropy Specification Inference from Demonstrations
Marcell Vazquez-Chanlatte, Sanjit A. Seshia
In many settings (e.g., robotics) demonstrations provide a natural way to specify tasks; however, most methods for learning from demonstrations either do not provide guarantees tha…
A Model Counter's Guide to Probabilistic Systems
Marcell Vazquez-Chanlatte, Markus N. Rabe, Sanjit A. Seshia
In this paper, we systematize the modeling of probabilistic systems for the purpose of analyzing them with model counting techniques. Starting from unbiased coin flips, we show how…
VERIFAI: A Toolkit for the Design and Analysis of Artificial Intelligence-Based Systems
Tommaso Dreossi, Daniel J. Fremont, Shromona Ghosh +4
We present VERIFAI, a software toolkit for the formal design and analysis of systems that include artificial intelligence (AI) and machine learning (ML) components. VERIFAI particu…
Time Series Learning using Monotonic Logical Properties
Marcell Vazquez-Chanlatte, Shromona Ghosh, Jyotirmoy V. Deshmukh +2
Cyber-physical systems of today are generating large volumes of time-series data. As manual inspection of such data is not tractable, the need for learning methods to help discover…
Learning Task Specifications from Demonstrations
Marcell Vazquez-Chanlatte, Susmit Jha, Ashish Tiwari +2
Real world applications often naturally decompose into several sub-tasks. In many settings (e.g., robotics) demonstrations provide a natural way to specify the sub-tasks. However,…
Tunable Reactive Synthesis for Lipschitz-Bounded Systems with Temporal Logic Specifications
Marcell Vazquez-Chanlatte, Shromona Ghosh, Vasumathi Raman +2
We address the problem of synthesizing reactive controllers for cyber-physical systems subject to Signal Temporal Logic (STL) specifications in the presence of adversarial inputs.…
Logic-based Clustering and Learning for Time-Series Data
Marcell Vazquez-Chanlatte, Jyotirmoy V. Deshmukh, Xiaoqing Jin +1
To effectively analyze and design cyberphysical systems (CPS), designers today have to combat the data deluge problem, i.e., the burden of processing intractably large amounts of d…