About

Lydia E. Kavraki is a University Professor and the Kenneth and Audrey Kennedy Professor of Computing at Rice University, where she also serves as a professor of Computer Science, Electrical & Computer Engineering, Mechanical Engineering, and Bioengineering. She is the director of the Ken Kennedy Institute at Rice University. Kavraki earned her B.A. in Computer Science from the University of Crete in Greece and her Ph.D. in Computer Science from Stanford University, working with Professor Jean-Claude Latombe. Her research broadly spans robotics, computational biomedicine, and physical AI, with a focus on developing methodologies for motion planning, reasoning under uncertainty, learning, and high-level robot instruction to enable robots to work seamlessly with humans. Her seminal work on sampling-based motion planning algorithms, including the Probabilistic Roadmap Planner, has significantly advanced the field, reducing planning times from minutes to seconds and achieving microsecond-level planning for complex manipulations. Her group has produced widely used open-source tools such as the Open Motion Planning Library (OMPL) and maintains several web servers for biomedical applications. Kavraki's research has been funded by numerous agencies including NSF, NIH, DOD, NASA, industry, and CPRIT. She has contributed to the development of robotic systems for space operations, such as NASA’s Robonaut2, and biomedical tools for protein structure modeling, drug discovery, and immunotherapy. Kavraki is a member of multiple prestigious academies, including the National Academy of Engineering, the National Academy of Sciences, and the American Academy of Arts and Sciences, and has received numerous awards, including the IEEE Frances E. Allen Medal and the ACM Grace Murray Hopper Award. Her work integrates algorithms, formal methods, machine learning, and physics modeling to advance the understanding of autonomous systems and their societal implications.

Research topics

• Computer Science
• Artificial Intelligence
• Machine Learning
• Engineering drawing
• Computational biology
• Engineering
• Mathematics
• Pharmacology
• Chemistry
• Biochemistry
• Biology
• Mechanical engineering
• Geography
• Cartography

Selected publications

• Ultrafast Sampling-based Kinodynamic Planning via Differential Flatness

  arXiv (Cornell University) · 2026-03-17

  preprintOpen accessSenior author

  Motion planning under dynamics constraints, i.e, kinodynamic planning, enables safe robot operation by generating dynamically feasible trajectories that the robot can accurately track. For high-DOF robots such as manipulators, sampling-based motion planners are commonly used, especially for complex tasks in cluttered environments. However, enforcing constraints on robot dynamics in such planners requires solving either challenging two-point boundary value problems (BVPs) or propagating robot dynamics, both of which cause computational bottlenecks that drastically increase planning times. Meanwhile, recent efforts have shown that sampling-based motion planners can generate plans in microseconds using parallelization, but are limited to geometric paths. This paper develops FLASK, a fast parallelized sampling-based kinodynamic motion planning framework for a broad class of differentially flat robot systems, including manipulators, ground and aerial vehicles, and more. Differential flatness allows us to transform the motion planning problem from the original state space to a flat output space, where an analytical time-parameterized solution of the BVP problem can be obtained. A trajectory in the flat output space is then converted back to a closed-form dynamically feasible trajectory in the original state space, enabling fast validation via ``single instruction, multiple data" parallelism. Our framework is fast, exact, and compatible with any sampling-based motion planner, while offering theoretical guarantees on probabilistic exhaustibility and asymptotic optimality based on the closed-form BVP solutions. We extensively verify the effectiveness of our approach in both simulated benchmarks and real experiments with cluttered and dynamic environments, requiring mere microseconds to milliseconds of planning time.

  PublisherDOI

• Efficient Multi-Robot Motion Planning for Manifold-Constrained Manipulators by Randomized Scheduling and Informed Path Generation

  IEEE Robotics and Automation Letters · 2026-02-09

  articleSenior author

  Multi-robot motion planning for high degree-offreedom manipulators in shared, constrained, and narrow spaces is a complex problem and essential for many scenarios such as construction, surgery, and more. Traditional coupled methods plan directly in the composite configuration space, which scales poorly; decoupled methods, on the other hand, plan separately for each robot but lack completeness. Hybrid methods that obtain paths from individual robots together require the enumeration of many paths before they can find valid composite solutions. This paper introduces Scheduling to Avoid Collisions (StAC), a hybrid approach that more effectively composes paths from individual robots by <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">scheduling</i> (adding stops and coordination motion along all paths) and generates paths that are likely to be feasible by using bidirectional feedback between the scheduler and motion planner for informed sampling. StAC uses 10 to 100 times fewer paths from the low-level planner than state-of-the-art hybrid baselines on challenging problems in manipulator cases.

  PublisherDOI

• TIDE: A Trace-Informed Depth-First Exploration for Planning with Temporally Extended Goals

  arXiv (Cornell University) · 2026-01-17

  preprintOpen access

  Task planning with temporally extended goals (TEGs) is a critical challenge in AI and robotics, enabling agents to achieve complex sequences of objectives over time rather than addressing isolated, immediate tasks. Linear Temporal Logic on finite traces (LTLf ) provides a robust formalism for encoding these temporal goals. Traditional LTLf task planning approaches often transform the temporal planning problem into a classical planning problem with reachability goals, which are then solved using off-the-shelf planners. However, these methods often lack informed heuristics to provide a guided search for temporal goals. We introduce TIDE (Trace-Informed Depth-first Exploration), a novel approach that addresses this limitation by decomposing a temporal problem into a sequence of smaller, manageable reach-avoid sub-problems, each solvable using an off-the-shelf planner. TIDE identifies and prioritizes promising automaton traces within the domain graph, using cost-driven heuristics to guide exploration. Its adaptive backtracking mechanism systematically recovers from failed plans by recalculating costs and penalizing infeasible transitions, ensuring completeness and efficiency. Experimental results demonstrate that TIDE achieves promising performance and is a valuable addition to the portfolio of planning methods for temporally extended goals.

  PublisherDOI

• Sampling-Based Motion Planning with Scene Graphs Under Perception Constraints

  Open MIND · 2026-03-03

  preprintSenior author

  It will be increasingly common for robots to operate in cluttered human-centered environments such as homes, workplaces, and hospitals, where the robot is often tasked to maintain perception constraints, such as monitoring people or multiple objects, for safety and reliability while executing its task. However, existing perception-aware approaches typically focus on low-degree-of-freedom (DoF) systems or only consider a single object in the context of high-DoF robots. This motivates us to consider the problem of perception-aware motion planning for high-DoF robots that accounts for multi-object monitoring constraints. We employ a scene graph representation of the environment, offering a great potential for incorporating long-horizon task and motion planning thanks to its rich semantic and spatial information. However, it does not capture perception-constrained information, such as the viewpoints the user prefers. To address these challenges, we propose MOPS-PRM, a roadmap-based motion planner, that integrates the perception cost of observing multiple objects or humans directly into motion planning for high-DoF robots. The perception cost is embedded to each object as part of a scene graph, and used to selectively sample configurations for roadmap construction, implicitly enforcing the perception constraints. Our method is extensively validated in both simulated and real-world experiments, achieving more than ~36% improvement in the average number of detected objects and ~17% better track rate against other perception-constrained baselines, with comparable planning times and path lengths.

  DOI

• Falsificationof Autonomous Systems in Rich Environments

  ACM Transactions on Cyber-Physical Systems · 2026-03-13

  articleOpen access

  Validating the behavior of autonomous Cyber-Physical Systems (CPS) and AI agents, which rely on automated controllers, is an objective of great importance. In recent years, Neural-Network (NN) controllers have been demonstrating great promise and experiencing tremendous popularity. Unfortunately, such learned controllers are often not certified and can cause the system to suffer from unpredictable or unsafe behavior. To mitigate this issue, a great effort has been dedicated to automated verification of systems. Specifically, works in the category of “black-box testing” rely on repeated system simulations to find a falsifying counterexample—a system run that violates a specification. As running high-fidelity simulations is computationally demanding, the goal of falsification approaches is to minimize the simulation effort needed to return a falsifying example. This often proves to be a great challenge, especially when the tested controller is well trained. This work contributes a novel falsification approach for autonomous systems under formal specification operating in uncertain environments. We are especially interested in CPS operating in rich, semantically defined, open environments, which yield high-dimensional, simulation-dependent sensor observations as inputs to the controller. Our approach introduces a novel reformulation of the falsification problem as the problem of planning a trajectory for a “meta-system,” which wraps and encapsulates the examined system; we call this approach: meta-planning. This approach results in testing fewer inputs, compared to serial input sampling, while making minimal assumptions on the system, and posing no limitation on the specification, environment, or controller, which is treated as a black-box. It also avoids redundant calculations and requires less effort for each test, by invoking only incremental updates to the autonomous-system’s trajectory at each iteration, using partial simulations. This formulation can be solved with standard sampling-based motion-planning techniques (like RRT), can gradually integrate domain knowledge to improve the search, based on its availability, and can even work with no domain knowledge at all. We support these ideas with an experimental study on falsification of an obstacle-avoiding autonomous car with a NN controller, where meta-planning demonstrates superior performance over alternative approaches.

  PublisherDOI

• Python Bindings for a Large C++ Robotics Library: The Case of OMPL

  Open MIND · 2026-03-04

  preprintSenior author

  Python bindings are a critical bridge between high-performance C++ libraries and the flexibility of Python, enabling rapid prototyping, reproducible experiments, and integration with simulation and learning frameworks in robotics research. Yet, generating bindings for large codebases is a tedious process that creates a heavy burden for a small group of maintainers. In this work, we investigate the use of Large Language Models (LLMs) to assist in generating nanobind wrappers, with human experts kept in the loop. Our workflow mirrors the structure of the C++ codebase, scaffolds empty wrapper files, and employs LLMs to fill in binding definitions. Experts then review and refine the generated code to ensure correctness, compatibility, and performance. Through a case study on a large C++ motion planning library, we document common failure modes, including mismanaging shared pointers, overloads, and trampolines, and show how in-context examples and careful prompt design improve reliability. Experiments demonstrate that the resulting bindings achieve runtime performance comparable to legacy solutions. Beyond this case study, our results provide general lessons for applying LLMs to binding generation in large-scale C++ projects.

  DOI

• Sampling-Based Motion Planning with Scene Graphs Under Perception Constraints

  ArXiv.org · 2026-03-03

  articleOpen accessSenior author

  It will be increasingly common for robots to operate in cluttered human-centered environments such as homes, workplaces, and hospitals, where the robot is often tasked to maintain perception constraints, such as monitoring people or multiple objects, for safety and reliability while executing its task. However, existing perception-aware approaches typically focus on low-degree-of-freedom (DoF) systems or only consider a single object in the context of high-DoF robots. This motivates us to consider the problem of perception-aware motion planning for high-DoF robots that accounts for multi-object monitoring constraints. We employ a scene graph representation of the environment, offering a great potential for incorporating long-horizon task and motion planning thanks to its rich semantic and spatial information. However, it does not capture perception-constrained information, such as the viewpoints the user prefers. To address these challenges, we propose MOPS-PRM, a roadmap-based motion planner, that integrates the perception cost of observing multiple objects or humans directly into motion planning for high-DoF robots. The perception cost is embedded to each object as part of a scene graph, and used to selectively sample configurations for roadmap construction, implicitly enforcing the perception constraints. Our method is extensively validated in both simulated and real-world experiments, achieving more than ~36% improvement in the average number of detected objects and ~17% better track rate against other perception-constrained baselines, with comparable planning times and path lengths.

  PublisherOA PDF

• FOXM1-Specific TCR-Engineered T Cells Target Non–Small Cell Lung Cancer

  Cancer Immunology Research · 2026-03-19

  articleOpen access

  FOXM1 is highly expressed in various cancer types and considered a key driver of cancer progression. Accordingly, we evaluated the immunogenicity of FOXM1 and investigated the feasibility of targeting this transcription factor using T cell receptor (TCR) engineering. We identified epitopes derived from FOXM1 which were immunogenic on HLA-A*02:01, HLA-A*24:02, and HLA-A*23:01, endogenously-processed and presented, and resulted in T cell activation and cytotoxic T cell responses. Following the generation of TCR-T cells, sensitivity and specificity were confirmed by peptide dose-response and X-scan, respectively. Most importantly, adoptive transfer of TCR engineered T cells led to a significant reduction in tumor growth, as well as significantly prolonged survival in a tumor-bearing immunocompromised murine model. Our studies confirm the immunogenicity of FOXM1 and feasibility of targeting this antigen using TCR-engineering.

  PublisherOA PDFDOI

• Python Bindings for a Large C++ Robotics Library: The Case of OMPL

  arXiv (Cornell University) · 2026-03-04

  articleOpen accessSenior author

  Python bindings are a critical bridge between high-performance C++ libraries and the flexibility of Python, enabling rapid prototyping, reproducible experiments, and integration with simulation and learning frameworks in robotics research. Yet, generating bindings for large codebases is a tedious process that creates a heavy burden for a small group of maintainers. In this work, we investigate the use of Large Language Models (LLMs) to assist in generating nanobind wrappers, with human experts kept in the loop. Our workflow mirrors the structure of the C++ codebase, scaffolds empty wrapper files, and employs LLMs to fill in binding definitions. Experts then review and refine the generated code to ensure correctness, compatibility, and performance. Through a case study on a large C++ motion planning library, we document common failure modes, including mismanaging shared pointers, overloads, and trampolines, and show how in-context examples and careful prompt design improve reliability. Experiments demonstrate that the resulting bindings achieve runtime performance comparable to legacy solutions. Beyond this case study, our results provide general lessons for applying LLMs to binding generation in large-scale C++ projects.

  PublisherOA PDF

• Ultrafast Sampling-based Kinodynamic Planning via Differential Flatness

  arXiv (Cornell University) · 2026-03-17

  articleOpen accessSenior author

  Motion planning under dynamics constraints, i.e, kinodynamic planning, enables safe robot operation by generating dynamically feasible trajectories that the robot can accurately track. For high-DOF robots such as manipulators, sampling-based motion planners are commonly used, especially for complex tasks in cluttered environments. However, enforcing constraints on robot dynamics in such planners requires solving either challenging two-point boundary value problems (BVPs) or propagating robot dynamics, both of which cause computational bottlenecks that drastically increase planning times. Meanwhile, recent efforts have shown that sampling-based motion planners can generate plans in microseconds using parallelization, but are limited to geometric paths. This paper develops FLASK, a fast parallelized sampling-based kinodynamic motion planning framework for a broad class of differentially flat robot systems, including manipulators, ground and aerial vehicles, and more. Differential flatness allows us to transform the motion planning problem from the original state space to a flat output space, where an analytical time-parameterized solution of the BVP problem can be obtained. A trajectory in the flat output space is then converted back to a closed-form dynamically feasible trajectory in the original state space, enabling fast validation via ``single instruction, multiple data" parallelism. Our framework is fast, exact, and compatible with any sampling-based motion planner, while offering theoretical guarantees on probabilistic exhaustibility and asymptotic optimality based on the closed-form BVP solutions. We extensively verify the effectiveness of our approach in both simulated benchmarks and real experiments with cluttered and dynamic environments, requiring mere microseconds to milliseconds of planning time.

  PublisherOA PDF

Recent grants

• RI: Small: A Novel Framework for Informed Manipulation Planning

  NSF · $441k · 2020–2024

• SHF: Medium: Automating robot programming through constraint solving and motion planning

  NSF · $816k · 2015–2021

• CSR/EHS: A Robotics-Inspired Approach for the Verification of Hybrid Systems

  NSF · $420k · 2006–2011

• Structure-based selection of tumor-antigens for T-cell based immunotherapy

  NIH · $182k · 2016–2018

• AF: Small: An Integrated Approach to Characterizing Conformational Changes of Large Proteins

  NSF · $458k · 2014–2017

Frequent coauthors

• Mark Moll

  97 shared

• Didier Devaurs

  49 shared

• Nicanor Silva

  Norwegian University of Science and Technology

  49 shared

• Jorge I. Poveda

  49 shared

• Dinler A. Antunes

  43 shared

• Cecilia Clementi

  41 shared

• Zachary Kingston

  35 shared

• Moshe Y. Vardi

  31 shared

Labs

• Kavraki LabPI

  Physical AI, Robotics & Biomedicine Lab

Awards & honors

• IEEE Frances E. Allen medal (2023)
• ACM Grace Murray Hopper Award (2000)
• ACM Athena Lecturer Award (2017)
• ACM/AAAI Allen Newell Award (2020)
• Early Academic Career Award from the IEEE Society on Robotic…