A5020074157- Formal Methods in Verification
- Modular Robots and Swarm Intelligence
- Robotic Path Planning Algorithms
- Model-Driven Software Engineering Techniques
- Robot Manipulation and Learning
- AI-based Problem Solving and Planning
- Logic, programming, and type systems
- Logic, Reasoning, and Knowledge
- Software Testing and Debugging Techniques
- Robotics and Automated Systems
- Distributed systems and fault tolerance
- Social Robot Interaction and HRI
- Distributed Control Multi-Agent Systems
- Reinforcement Learning in Robotics
- Real-Time Systems Scheduling
- Petri Nets in System Modeling
- Semantic Web and Ontologies
- Micro and Nano Robotics
- Natural Language Processing Techniques
- Machine Learning and Algorithms
- Embedded Systems Design Techniques
- Optimization and Search Problems
- Multimodal Machine Learning Applications
- Speech and dialogue systems
- Bayesian Modeling and Causal Inference
Cornell University
2016-2025
Ithaca College
2025
Sibley Memorial Hospital
2012-2022
Corvallis Environmental Center
2020
University of Pennsylvania
2006-2018
Robotics Research (United States)
2016-2018
Smithsonian Institution
2011
K.N.Toosi University of Technology
2011
Philadelphia University
2007
This paper provides a framework <i xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">to automatically</i> generate hybrid controller that xmlns:xlink="http://www.w3.org/1999/xlink">guarantees</i> the robot can achieve its task when model, class of admissible environments, and high-level or behavior for are provided. The desired specifications, which expressed in fragment linear temporal logic (LTL), capture complex behaviors such as search rescue,...
This article surveys the use of natural language in robotics from a point view. To human language, robots must map words to aspects physical world, mediated by robot's sensors and actuators. problem differs other processing domains due need ground noisy percepts actions. Here, we describe central robots, including understanding requests, using drive learning about engaging collaborative dialogue with partner. We common approaches, roughly divided into methods, logic-based methods that focus...
In this paper, we consider the problem of robot motion planning in order to satisfy formulas expressible temporal logics. Temporal logics naturally express traditional specifications such as reaching a goal or avoiding an obstacle, but also more sophisticated sequencing, coverage, ordering different tasks. provide computational solutions problem, first construct discrete abstractions based on some environmental decomposition. We then generate plans satisfying logic formula using powerful...
Given a robot model and class of admissible environments, this paper provides framework for automatically verifiably composing controllers that satisfy high level task specifications expressed in suitable temporal logics. The desired can express complex behaviors such as search rescue, coverage, collision avoidance. In addition, our explicitly captures sensor depend on the environment with which is interacting, resulting novel paradigm sensor-based logic motion planning. As one part another...
Robot motion planning algorithms have focused on low-level reachability goals taking into account robot kinematics, or high level task while ignoring dynamics. In this paper, we present an integrated approach to the design of closed–loop hybrid controllers that guarantee by construction resulting continuous trajectories satisfy sophisticated specifications expressed in so–called Linear Temporal Logic. addition, our framework ensures temporal logic specification is satisfied even presence...
The Linear Temporal Logic MissiOn Planning (LTLMoP) toolkit is a software package designed to assist in the rapid development, implementation, and testing of high-level robot controllers. In this toolkit, structured English are used write reactive task specifications, which then automatically transformed into correct controllers that can be drive either simulated or real robot. LTLMoP's modular design makes it ideal for research areas such as controller synthesis, semantic parsing, motion...
Recently, Linear Temporal Logic (LTL) has been successfully applied to high-level task and motion planning problems for mobile robots. One of the main attributes LTL is its close relationship with fragments natural language. In this paper, we take first steps toward building a language interface methods robots as application domain. For purpose, built structured English which maps directly fragment LTL.
Robot control for tasks such as moving around obstacles or grasping objects has advanced significantly in the last few decades. However, controlling robots to perform complex is still accomplished largely by highly trained programmers a manual, time-consuming, and error-prone process that typically validated only through extensive testing. Formal methods are mathematical techniques reasoning about systems, their requirements, guarantees. synthesis robotics refers frameworks specifying...
In this article, we presented an overview of how temporal logic synthesis, coupled with abstractions and continuous bisimilar controllers, can be used to generate high-level, reactive robot control. We illustrated the ideas using DUC mission, two approaches deal inherent state explosion problem.
This paper introduces a motion-planning framework for hybrid system with general continuous dynamics to satisfy temporal logic specification consisting of cosafety and safety components in partially unknown environment. The employs multilayered synergistic planner generate trajectories that the adopt an iterative replanning strategy deal obstacles. When discovery obstacle renders unsatisfiable, division between constraints is considered. component treated as soft constraint, whose partial...
A robot autonomously completes tasks by transforming its body to match capabilities newly encountered environments.
This paper considers the problem of motion planning for a hybrid robotic system with complex and nonlinear dynamics in partially unknown environment given temporal logic specification. We employ multi-layered synergistic framework that can deal general robot combine it an iterative strategy. Our work allows us to environmental restrictions only when they are discovered without need repeat computation is related In addition, we define metric satisfaction use this plan trajectory satisfies...
In the near future mobile robots, such as personal robots or manipulators, will share workspace with other and humans. We present a method for mission motion planning that applies to small teams of performing task in an environment moving obstacles, Given specification written linear temporal logic, patrolling set rooms, we synthesize automaton from which can extract valid strategies. This centralized is executed by team at runtime, conjunction distributed planner guarantees avoidance...
What would it be like if we could give our robot high level commands and automatically execute them in a verifiably correct fashion dynamically changing environments? This work demonstrates method for generating continuous feedback control inputs that satisfy high-level specifications. Using collection of local policies concert with synthesized discrete automaton, this paper the approach on an Ackermann-steered vehicle satisfies command "drive around until you find empty parking space, then...
This paper addresses the challenge of enabling nonexpert users to command robots perform complex high-level tasks using natural language.It describes an integrated system that combines power formal methods with accessibility language, providing correct-by-construction controllers for specifications can be implemented, and easy-to-understand feedback user on those cannot achieved.This is among first works close this loop, interact robot in order identify a succinct cause failure obtain...
JESSIE is a robotic system that enables novice programmers to program social robots by expressing high-level specifications. We employ control synthesis with tangible front-end allow users define complex behavior for which we automatically generate code. demonstrate in the context of enabling clinicians create personalized treatments people mild cognitive impairment (MCI) on Kuri robot, little time and without error. evaluated neuropsychologists who reported high usability learnability. They...
As robots begin to interact closely with humans, we need build systems worthy of trust regarding the safety and quality interaction.
We propose a new specification language and control synthesis technique for single multi-robot high-level tasks; these tasks include timing constraints reaction to environmental events. Specifically, we define Event-based Signal Temporal Logic (STL) use it encode that are reactive uncontrolled environment Our approach STL combines automata barrier functions produce robot behaviors satisfy the when possible. method automatically provides feedback user if an task can not be achieved....
Given a collaborative high-level task and team of heterogeneous robots with behaviors to satisfy it, this work focuses on the challenge automatically adjusting individual robot at runtime such that is still satisfied. We specifically address scenarios when encounter changes their abilities–either failures or additional actions they can perform. aim minimize global teaming reassignments (and as result, local resynthesis) robots' capabilities change. The tasks are encoded in LTL...
Abstract In this paper, we present a framework that automatically selects modular manipulator structure based on user-defined task involving 3D trajectory tracking, handling heavy payloads with precision, and navigating around obstacles. For such tasks, hybrid structures combining serial parallel components may offer advantages, leveraging the large reachable space of elements rigidity for enhanced accuracy. Given challenges in developing comprehensive method kinematic design dynamic...