Search Results for author: Calin Belta

Found 40 papers, 4 papers with code

Technical Report: Distribution Temporal Logic: Combining Correctness with Quality of Estimation

no code implementations9 Sep 2013 Austin Jones, Mac Schwager, Calin Belta

We present a new temporal logic called Distribution Temporal Logic (DTL) defined over predicates of belief states and hidden states of partially observable systems.

A Formal Methods Approach to Pattern Synthesis in Reaction Diffusion Systems

no code implementations12 Sep 2014 Ebru Aydin Gol, Ezio Bartocci, Calin Belta

We propose a technique to detect and generate patterns in a network of locally interacting dynamical systems.

Time Window Temporal Logic

2 code implementations13 Feb 2016 Cristian-Ioan Vasile, Derya Aksaray, Calin Belta

This paper introduces time window temporal logic (TWTL), a rich expressivity language for describing various time bounded specifications.

Formal Languages and Automata Theory Logic in Computer Science

A Hierarchical Reinforcement Learning Method for Persistent Time-Sensitive Tasks

no code implementations20 Jun 2016 Xiao Li, Calin Belta

Reinforcement learning has been applied to many interesting problems such as the famous TD-gammon and the inverted helicopter flight.

Hierarchical Reinforcement Learning reinforcement-learning +1

Q-Learning for Robust Satisfaction of Signal Temporal Logic Specifications

no code implementations23 Sep 2016 Derya Aksaray, Austin Jones, Zhaodan Kong, Mac Schwager, Calin Belta

This paper addresses the problem of learning optimal policies for satisfying signal temporal logic (STL) specifications by agents with unknown stochastic dynamics.

Systems and Control

Reinforcement Learning With Temporal Logic Rewards

no code implementations11 Dec 2016 Xiao Li, Cristian-Ioan Vasile, Calin Belta

We propose Truncated Linear Temporal Logic (TLTL) as specifications language, that is arguably well suited for the robotics applications, together with quantitative semantics, i. e., robustness degree.

reinforcement-learning Reinforcement Learning (RL)

Automata-Guided Hierarchical Reinforcement Learning for Skill Composition

no code implementations31 Oct 2017 Xiao Li, Yao Ma, Calin Belta

Skills learned through (deep) reinforcement learning often generalizes poorly across domains and re-training is necessary when presented with a new task.

Hierarchical Reinforcement Learning reinforcement-learning +1

AUTOMATA GUIDED HIERARCHICAL REINFORCEMENT LEARNING FOR ZERO-SHOT SKILL COMPOSITION

no code implementations ICLR 2018 Xiao Li, Yao Ma, Calin Belta

An obstacle that prevents the wide adoption of (deep) reinforcement learning (RL) in control systems is its need for a large number of interactions with the environment in order to master a skill.

Hierarchical Reinforcement Learning reinforcement-learning +1

Automata Guided Reinforcement Learning With Demonstrations

no code implementations17 Sep 2018 Xiao Li, Yao Ma, Calin Belta

Tasks with complex temporal structures and long horizons pose a challenge for reinforcement learning agents due to the difficulty in specifying the tasks in terms of reward functions as well as large variances in the learning signals.

reinforcement-learning Reinforcement Learning (RL)

Control from Signal Temporal Logic Specifications with Smooth Cumulative Quantitative Semantics

1 code implementation25 Apr 2019 Iman Haghighi, Noushin Mehdipour, Ezio Bartocci, Calin Belta

We present a framework to synthesize control policies for nonlinear dynamical systems from complex temporal constraints specified in a rich temporal logic called Signal Temporal Logic (STL).

Systems and Control

Automata Guided Skill Composition

no code implementations ICLR 2019 Xiao Li, Yao Ma, Calin Belta

Skills learned through (deep) reinforcement learning often generalizes poorly across tasks and re-training is necessary when presented with a new task.

reinforcement-learning Reinforcement Learning (RL)

Distributed and Consistent Multi-Image Feature Matching via QuickMatch

no code implementations29 Oct 2019 Zachary Serlin, Guang Yang, Brandon Sookraj, Calin Belta, Roberto Tron

The centralized QuickMatch algorithm is compared to other standard matching algorithms, while the Distributed QuickMatch algorithm is compared to the centralized algorithm in terms of preservation of match consistency.

Object object-detection +2

How Retroactivity Affects the Behavior of Incoherent Feed-Forward Loops

no code implementations15 Jul 2020 Junmin Wang, Calin Belta, Samuel A. Isaacson

We compare the behaviors of IFFLs to negative autoregulatory loops, another sign-sensitive response-accelerating network motif, and find that increasing retroactivity in a negative autoregulated circuit can only slow the response.

Open-Ended Question Answering

Recurrent Neural Network Controllers for Signal Temporal Logic Specifications Subject to Safety Constraints

no code implementations24 Sep 2020 Wenliang Liu, Noushin Mehdipour, Calin Belta

We propose a framework based on Recurrent Neural Networks (RNNs) to determine an optimal control strategy for a discrete-time system that is required to satisfy specifications given as Signal Temporal Logic (STL) formulae.

Rule-based Optimal Control for Autonomous Driving

no code implementations14 Jan 2021 Wei Xiao, Noushin Mehdipour, Anne Collin, Amitai Bin-Nun, Emilio Frazzoli, Radboud Duintjer Tebbens, Calin Belta

We develop optimal control strategies for Autonomous Vehicles (AVs) that are required to meet complex specifications imposed by traffic laws and cultural expectations of reasonable driving behavior.

Autonomous Driving Robotics Systems and Control Systems and Control

Model-Based Reinforcement Learning for Approximate Optimal Control with Temporal Logic Specifications

no code implementations18 Jan 2021 Max Cohen, Calin Belta

In this paper we study the problem of synthesizing optimal control policies for uncertain continuous-time nonlinear systems from syntactically co-safe linear temporal logic (scLTL) formulas.

Model-based Reinforcement Learning reinforcement-learning +1

Experimental Validation of Linear and Nonlinear MPC on an Articulated Unmanned Ground Vehicle

no code implementations25 Mar 2021 Erkan Kayacan, Wouter Saeys, Herman Ramon, Calin Belta, Joshua M. Peschel

The experimental results for a time-based trajectory show that the NMHE-NMPC framework with the proposed real-time iteration scheme gives better trajectory tracking performance than the ISL-LMPC framework and the required computation time is feasible for real-time applications.

Model Predictive Control

Safe Model-based Control from Signal Temporal Logic Specifications Using Recurrent Neural Networks

no code implementations29 Mar 2021 Wenliang Liu, Mirai Nishioka, Calin Belta

To capture the history dependency of STL specifications, we use a recurrent neural network (RNN) to implement the control policy.

Event-Triggered Safety-Critical Control for Systems with Unknown Dynamics

no code implementations29 Mar 2021 Wei Xiao, Calin Belta, Christos G. Cassandras

We define a HOCBF for a safety requirement on the unmodelled system based on the adaptive dynamics and error states, and reformulate the safety-critical control problem as the above mentioned QP.

Neural Network-based Control for Multi-Agent Systems from Spatio-Temporal Specifications

no code implementations6 Apr 2021 Suhail Alsalehi, Noushin Mehdipour, Ezio Bartocci, Calin Belta

We propose a framework for solving control synthesis problems for multi-agent networked systems required to satisfy spatio-temporal specifications.

Safe Exploration in Model-based Reinforcement Learning using Control Barrier Functions

no code implementations16 Apr 2021 Max H. Cohen, Calin Belta

This paper develops a model-based reinforcement learning (MBRL) framework for learning online the value function of an infinite-horizon optimal control problem while obeying safety constraints expressed as control barrier functions (CBFs).

Model-based Reinforcement Learning reinforcement-learning +2

Inferring Temporal Logic Properties from Data using Boosted Decision Trees

no code implementations24 May 2021 Erfan Aasi, Cristian Ioan Vasile, Mahroo Bahreinian, Calin Belta

Many autonomous systems, such as robots and self-driving cars, involve real-time decision making in complex environments, and require prediction of future outcomes from limited data.

Autonomous Driving Decision Making +3

Classification of Time-Series Data Using Boosted Decision Trees

1 code implementation1 Oct 2021 Erfan Aasi, Cristian Ioan Vasile, Mahroo Bahreinian, Calin Belta

Our algorithm leverages an ensemble of Concise Decision Trees (CDTs) to improve the classification performance, where each CDT is a decision tree that is empowered by a set of techniques to generate simpler formulae and improve interpretability.

Autonomous Driving Classification +3

Learning Spatio-Temporal Specifications for Dynamical Systems

no code implementations20 Dec 2021 Suhail Alsalehi, Erfan Aasi, Ron Weiss, Calin Belta

In addition, given system requirements in the form of SVM-STL specifications, we provide an approach for parameter synthesis to find parameters that maximize the satisfaction of such specifications.

Formal Logic

Time-Incremental Learning from Data Using Temporal Logics

no code implementations28 Dec 2021 Erfan Aasi, Mingyu Cai, Cristian Ioan Vasile, Calin Belta

In this paper, we introduce a time-incremental learning framework: given a dataset of labeled signal traces with a common time horizon, we propose a method to predict the label of a signal that is received incrementally over time, referred to as prefix signal.

Decision Making Incremental Learning +1

Overcoming Exploration: Deep Reinforcement Learning for Continuous Control in Cluttered Environments from Temporal Logic Specifications

no code implementations28 Jan 2022 Mingyu Cai, Erfan Aasi, Calin Belta, Cristian-Ioan Vasile

This work presents a deep policy gradient algorithm for controlling a robot with unknown dynamics operating in a cluttered environment when the task is specified as a Linear Temporal Logic (LTL) formula.

Continuous Control reinforcement-learning +2

High Order Robust Adaptive Control Barrier Functions and Exponentially Stabilizing Adaptive Control Lyapunov Functions

no code implementations3 Mar 2022 Max H. Cohen, Calin Belta

We first introduce the notion of a High Order Robust Adaptive Control Barrier Function (HO-RaCBF) as a means to compute control policies guaranteeing satisfaction of high relative degree safety constraints in the face of parametric model uncertainty.

Distributed Control using Reinforcement Learning with Temporal-Logic-Based Reward Shaping

no code implementations8 Mar 2022 Ningyuan Zhang, Wenliang Liu, Calin Belta

We present a computational framework for synthesis of distributed control strategies for a heterogeneous team of robots in a partially observable environment.

reinforcement-learning Reinforcement Learning (RL)

Decentralized Signal Temporal Logic Control for Perturbed Interconnected Systems via Assume-Guarantee Contract Optimization

no code implementations30 Jun 2022 Kasra Ghasemi, Sadra Sadraddini, Calin Belta

We develop a novel decentralized control method for a network of perturbed linear systems with dynamical couplings subject to Signal Temporal Logic (STL) specifications.

Compositional Synthesis for Linear Systems via Convex Optimization of Assume-Guarantee Contracts

no code implementations2 Aug 2022 Kasra Ghasemi, Sadra Sadraddini, Calin Belta

We take a divide and conquer approach to design controllers for reachability problems given large-scale linear systems with polyhedral constraints on states, controls, and disturbances.

Model Predictive Control

Robust Multi-Agent Coordination from CaTL+ Specifications

no code implementations4 Oct 2022 Wenliang Liu, Kevin Leahy, Zachary Serlin, Calin Belta

We consider the problem of controlling a heterogeneous multi-agent system required to satisfy temporal logic requirements.

CatlNet: Learning Communication and Coordination Policies from CaTL+ Specifications

no code implementations30 Nov 2022 Wenliang Liu, Kevin Leahy, Zachary Serlin, Calin Belta

In this paper, we propose a learning-based framework to simultaneously learn the communication and distributed control policies for a heterogeneous multi-agent system (MAS) under complex mission requirements from Capability Temporal Logic plus (CaTL+) specifications.

Modular Adaptive Safety-Critical Control

no code implementations7 Mar 2023 Max Cohen, Calin Belta

We demonstrate that the unification of ISS and ISSf in an adaptive control setting allows for maintaining a single set of parameter estimates for both the CLF and CBF that can be generated by a class of update laws satisfying a few general properties.

Uncertainty Quantification for Recursive Estimation in Adaptive Safety-Critical Control

no code implementations4 Apr 2023 Max H. Cohen, Makai Mann, Kevin Leahy, Calin Belta

In this paper, we present a framework for online parameter estimation and uncertainty quantification in the context of adaptive safety-critical control.

Uncertainty Quantification

Learning Robust and Correct Controllers from Signal Temporal Logic Specifications Using BarrierNet

no code implementations12 Apr 2023 Wenliang Liu, Wei Xiao, Calin Belta

In this paper, we consider the problem of learning a neural network controller for a system required to satisfy a Signal Temporal Logic (STL) specification.

Control-Based Planning over Probability Mass Function Measurements via Robust Linear Programming

no code implementations12 Oct 2023 Mehdi Kermanshah, Calin Belta, Roberto Tron

Using the strong duality of linear programs (LPs) and robust optimization, we convert the optimization problem to a linear program that can be efficiently solved offline.

Interpretable Generative Adversarial Imitation Learning

no code implementations15 Feb 2024 Wenliang Liu, Danyang Li, Erfan Aasi, Roberto Tron, Calin Belta

Imitation learning methods have demonstrated considerable success in teaching autonomous systems complex tasks through expert demonstrations.

Generative Adversarial Network Imitation Learning

Cannot find the paper you are looking for? You can Submit a new open access paper.