About

Professor Kostas Bekris leads the PRACSYS Lab at Rutgers University, focusing on research in robot learning, perception, and planning. His work emphasizes applications in manipulation and navigation for logistics, search and rescue, and service robotics. A particular area of interest is the development of novel soft mechanisms and robots that exhibit significant dynamics. The PRACSYS Lab, under his guidance, integrates physics-aware research for autonomous computational systems, reflecting a practical approach to robotics inspired by the concept of praxis from Ancient Greek philosophy. Professor Bekris is affiliated with the Computer Science Department, CBIM Research Center, RU Center for Cognitive Science, and CCICADA DHS Center of Excellence at Rutgers, contributing to interdisciplinary advancements in robotics and autonomous systems.

Research topics

• Computer Science
• Artificial Intelligence
• Human–computer interaction
• Computer vision
• Engineering
• Engineering drawing
• Psychology
• Materials science
• Mathematics
• Simulation
• Control engineering
• Mechanical engineering
• Physical medicine and rehabilitation
• Social psychology
• Industrial engineering
• Embedded system
• Medicine
• Systems engineering

Selected publications

• Robust Out-of-Order Retrieval for Grid-Based Storage at Maximum Capacity

  Open MIND · 2026-01-27

  preprintSenior author

  This paper proposes a framework for improving the operational efficiency of automated storage systems under uncertainty. It considers a 2D grid-based storage for uniform-sized loads (e.g., containers, pallets, or totes), which are moved by a robot (or other manipulator) along a collision-free path in the grid. The loads are labeled (i.e., unique) and must be stored in a given sequence, and later be retrieved in a different sequence -- an operational pattern that arises in logistics applications, such as last-mile distribution centers and shipyards. The objective is to minimize the load relocations to ensure efficient retrieval. A previous result guarantees a zero-relocation solution for known storage and retrieval sequences, even for storage at full capacity, provided that the side of the grid through which loads are stored/retrieved is at least 3 cells wide. However, in practice, the retrieval sequence can change after the storage phase. To address such uncertainty, this work investigates \emph{$k$-bounded perturbations} during retrieval, under which any two loads may depart out of order if they are originally at most $k$ positions apart. We prove that a $Θ(k)$ grid width is necessary and sufficient for eliminating relocations at maximum capacity. We also provide an efficient solver for computing a storage arrangement that is robust to such perturbations. To address the higher-uncertainty case where perturbations exceed $k$, a strategy is introduced to effectively minimize relocations. Extensive experiments show that, for $k$ up to half the grid width, the proposed storage-retrieval framework essentially eliminates relocations. For $k$ values up to the full grid width, relocations are reduced by $50\%+$.

  DOI

• State and Trajectory Estimation of Tensegrity Robots via Factor Graphs and Chebyshev Polynomials

  arXiv (Cornell University) · 2026-04-09

  articleOpen accessSenior author

  Tensegrity robots offer compliance and adaptability, but their nonlinear, and underconstrained dynamics make state estimation challenging. Reliable continuous-time estimation of all rigid links is crucial for closed-loop control, system identification, and machine learning; however, conventional methods often fall short. This paper proposes a two-stage approach for robust state or trajectory estimation (i.e., filtering or smoothing) of a cable-driven tensegrity robot. For online state estimation, this work introduces a factor-graph-based method, which fuses measurements from an RGB-D camera with on-board cable length sensors. To the best of the authors' knowledge, this is the first application of factor graphs in this domain. Factor graphs are a natural choice, as they exploit the robot's structural properties and provide effective sensor fusion solutions capable of handling nonlinearities in practice. Both the Mahalanobis distance-based clustering algorithm, used to handle noise, and the Chebyshev polynomial method, used to estimate the most probable velocities and intermediate states, are shown to perform well on simulated and real-world data, compared to an ICP-based algorithm. Results show that the approach provides high fidelity, continuous-time state and trajectory estimates for complex tensegrity robot motions.

  PublisherOA PDF

• CableRobotGraphSim: A Graph Neural Network for Modeling Partially Observable Cable-Driven Robot Dynamics

  ArXiv.org · 2026-02-24

  articleOpen access

  General-purpose simulators have accelerated the development of robots. Traditional simulators based on first-principles, however, typically require full-state observability or depend on parameter search for system identification. This work presents \texttt{CableRobotGraphSim}, a novel Graph Neural Network (GNN) model for cable-driven robots that aims to address shortcomings of prior simulation solutions. By representing cable-driven robots as graphs, with the rigid-bodies as nodes and the cables and contacts as edges, this model can quickly and accurately match the properties of other simulation models and real robots, while ingesting only partially observable inputs. Accompanying the GNN model is a sim-and-real co-training procedure that promotes generalization and robustness to noisy real data. This model is further integrated with a Model Predictive Path Integral (MPPI) controller for closed-loop navigation, which showcases the model's speed and accuracy.

  PublisherOA PDF

• State and Trajectory Estimation of Tensegrity Robots via Factor Graphs and Chebyshev Polynomials

  arXiv (Cornell University) · 2026-04-09

  preprintOpen accessSenior author

  Tensegrity robots offer compliance and adaptability, but their nonlinear, and underconstrained dynamics make state estimation challenging. Reliable continuous-time estimation of all rigid links is crucial for closed-loop control, system identification, and machine learning; however, conventional methods often fall short. This paper proposes a two-stage approach for robust state or trajectory estimation (i.e., filtering or smoothing) of a cable-driven tensegrity robot. For online state estimation, this work introduces a factor-graph-based method, which fuses measurements from an RGB-D camera with on-board cable length sensors. To the best of the authors' knowledge, this is the first application of factor graphs in this domain. Factor graphs are a natural choice, as they exploit the robot's structural properties and provide effective sensor fusion solutions capable of handling nonlinearities in practice. Both the Mahalanobis distance-based clustering algorithm, used to handle noise, and the Chebyshev polynomial method, used to estimate the most probable velocities and intermediate states, are shown to perform well on simulated and real-world data, compared to an ICP-based algorithm. Results show that the approach provides high fidelity, continuous-time state and trajectory estimates for complex tensegrity robot motions.

  PublisherDOI

• An Open-Source, Reproducible Tensegrity Robot That Can Navigate Among Obstacles

  IEEE Robotics and Automation Letters · 2026-04-06 · 1 citations

  articleSenior author

  Tensegrity robots, composed of rigid struts and elastic tendons, provide impact resistance, low mass, and adaptability to unstructured terrain. Their compliance and complex, coupled dynamics, however, present modeling and control challenges, hindering planning and obstacle avoidance. This paper presents a complete, open-source, and reproducible system that enables navigation for a 3-bar tensegrity robot. The system comprises: (i) an inexpensive, open-source hardware design, and (ii) an integrated, open-source software stack for physics-based modeling, system identification, state estimation, path planning, and control. All hardware and software are publicly available at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://tensegrity.yale.edu/</uri> tensegrity.yale.edu. The proposed system tracks the robot using a static overhead camera and executes collision-free paths to a goal among known obstacle locations. System robustness is demonstrated through experiments involving unmodeled environmental challenges, including a vertical drop, an incline, and granular media, culminating in an outdoor field demonstration. To validate reproducibility, experiments were conducted using robot instances at two different laboratories. This work provides the robotics community with a complete navigation system for a compliant, impact-resistant, and shape-morphing robot. This system is intended to serve as a springboard for advancing the navigation capabilities of other unconventional robotic platforms.

  PublisherDOI

• Robust Out-of-Order Retrieval for Grid-Based Storage at Maximum Capacity

  ArXiv.org · 2026-01-27

  articleOpen accessSenior author

  This paper proposes a framework for improving the operational efficiency of automated storage systems under uncertainty. It considers a 2D grid-based storage for uniform-sized loads (e.g., containers, pallets, or totes), which are moved by a robot (or other manipulator) along a collision-free path in the grid. The loads are labeled (i.e., unique) and must be stored in a given sequence, and later be retrieved in a different sequence -- an operational pattern that arises in logistics applications, such as last-mile distribution centers and shipyards. The objective is to minimize the load relocations to ensure efficient retrieval. A previous result guarantees a zero-relocation solution for known storage and retrieval sequences, even for storage at full capacity, provided that the side of the grid through which loads are stored/retrieved is at least 3 cells wide. However, in practice, the retrieval sequence can change after the storage phase. To address such uncertainty, this work investigates \emph{$k$-bounded perturbations} during retrieval, under which any two loads may depart out of order if they are originally at most $k$ positions apart. We prove that a $Θ(k)$ grid width is necessary and sufficient for eliminating relocations at maximum capacity. We also provide an efficient solver for computing a storage arrangement that is robust to such perturbations. To address the higher-uncertainty case where perturbations exceed $k$, a strategy is introduced to effectively minimize relocations. Extensive experiments show that, for $k$ up to half the grid width, the proposed storage-retrieval framework essentially eliminates relocations. For $k$ values up to the full grid width, relocations are reduced by $50\%+$.

  PublisherOA PDF

• CableRobotGraphSim: A Graph Neural Network for Modeling Partially Observable Cable-Driven Robot Dynamics

  Open MIND · 2026-02-24

  preprint

  General-purpose simulators have accelerated the development of robots. Traditional simulators based on first-principles, however, typically require full-state observability or depend on parameter search for system identification. This work presents \texttt{CableRobotGraphSim}, a novel Graph Neural Network (GNN) model for cable-driven robots that aims to address shortcomings of prior simulation solutions. By representing cable-driven robots as graphs, with the rigid-bodies as nodes and the cables and contacts as edges, this model can quickly and accurately match the properties of other simulation models and real robots, while ingesting only partially observable inputs. Accompanying the GNN model is a sim-and-real co-training procedure that promotes generalization and robustness to noisy real data. This model is further integrated with a Model Predictive Path Integral (MPPI) controller for closed-loop navigation, which showcases the model's speed and accuracy.

  DOI

• Kinodynamic Trajectory Following with STELA: Simultaneous Trajectory Estimation &amp; Local Adaptation

  ArXiv.org · 2025-04-28

  preprintOpen accessSenior author

  State estimation and control are often addressed separately, leading to unsafe execution due to sensing noise, execution errors, and discrepancies between the planning model and reality. Simultaneous control and trajectory estimation using probabilistic graphical models has been proposed as a unified solution to these challenges. Previous work, however, relies heavily on appropriate Gaussian priors and is limited to holonomic robots with linear time-varying models. The current research extends graphical optimization methods to vehicles with arbitrary dynamical models via Simultaneous Trajectory Estimation and Local Adaptation (STELA). The overall approach initializes feasible trajectories using a kinodynamic, sampling-based motion planner. Then, it simultaneously: (i) estimates the past trajectory based on noisy observations, and (ii) adapts the controls to be executed to minimize deviations from the planned, feasible trajectory, while avoiding collisions. The proposed factor graph representation of trajectories in STELA can be applied for any dynamical system given access to first or second-order state update equations, and introduces the duration of execution between two states in the trajectory discretization as an optimization variable. These features provide both generalization and flexibility in trajectory following. In addition to targeting computational efficiency, the proposed strategy performs incremental updates of the factor graph using the iSAM algorithm and introduces a time-window mechanism. This mechanism allows the factor graph to be dynamically updated to operate over a limited history and forward horizon of the planned trajectory. This enables online updates of controls at a minimum of 10Hz. Experiments demonstrate that STELA achieves at least comparable performance to previous frameworks on idealized vehicles with linear dynamics.[...]

  PublisherOA PDFDOI

• PROBE: Proprioceptive Obstacle Detection and Estimation while Navigating in Clutter

  2025-05-19

  article

  In critical applications, including search-and-rescue in degraded environments, blockages can be prevalent and prevent the effective deployment of certain sensing modalities, particularly vision, due to occlusion and the constrained range of view of onboard camera sensors. To enable robots to tackle these challenges, we propose a new approach, Proprioceptive Obstacle Detection and Estimation while navigating in clutter (PROBE), which instead relies only on the robot's proprioception to infer the presence or absence of occluded rectangular obstacles while predicting their dimensions and poses in SE (2). The proposed approach is a Transformer neural network that receives as input a history of applied torques and sensed whole-body movements of the robot and returns a parameterized representation of the obstacles in the environment. The effectiveness of PROBE is evaluated on simulated environments in Isaac Gym and with a real Unitree Go1 quadruped robot. The project webpage can be found at https://dhruvmetha.github.io/legged-probe/.

  PublisherDOI

• Integrating Model-Based Control and RL for Sim2Real Transfer of Tight Insertion Policies

  2025-05-19 · 1 citations

  articleSenior author

  Object insertion under tight tolerances (<Imm) is an important but challenging assembly task as even small errors can result in undesirable contacts. Recent efforts focused on Reinforcement Learning (RL), which often depends on careful definition of dense reward functions. This work proposes an effective strategy for such tasks that integrates traditional model-based control with RL to achieve improved insertion accuracy. The policy is trained exclusively in simulation and is zero-shot transferred to the real system. It employs a potential field-based controller to acquire a model-based policy for inserting a plug into a socket given full observability in simulation. This policy is then integrated with residual RL, which is trained in simulation given only a sparse, goal-reaching reward. A curriculum scheme over observation noise and action magnitude is used for training the residual RL policy. Both policy components use as input the SE(3) poses of both the plug and the socket and return the plug's SE (3) pose transform, which is executed by a robotic arm using a controller. The integrated policy is deployed on the real system without further training or fine-tuning, given a visual SE (3) object tracker. The proposed solution and alternatives are evaluated across a variety of objects and conditions in simulation and reality. The proposed approach outperforms recent RL-based methods in this domain and prior efforts with hybrid policies. Ablations highlight the impact of each component of the approach. For more information please refer to the corresponding website.

  PublisherDOI

Recent grants

• Collaborative Research: RI: Medium: Robust Assembly of Compliant Modular Robots

  NSF · $386k · 2020–2026

• NRI: INT: COLLAB: Integrated Modeling and Learning for Robust Grasping and Dexterous Manipulation with Adaptive Hands

  NSF · $868k · 2017–2023

• BSF:2012166:A Framework for Composite Techniques in Motion Planning

  NSF · $40k · 2013–2018

• RI: Small: Taming Combinatorial Challenges in Multi-Object Manipulation

  NSF · $468k · 2016–2020

• EAGER: Provably Efficient Motion Planning After Finite Computation Time

  NSF · $175k · 2014–2017

Frequent coauthors

• Abdeslam Boularias

  42 shared

• Rahul Shome

  42 shared

• Chaitanya Mitash

  Amazon (United States)

  34 shared

• Bowen Wen

  28 shared

• Jingjin Yu

  23 shared

• Lydia E. Kavraki

  23 shared

• Athanasios Krontiris

  23 shared

• Andrew Kimmel

  Rutgers, The State University of New Jersey

  22 shared

Labs

• PRACSYS LabPI

  Research in robot learning, perception, and planning

Education

• Ph.D., Computer Science

  Rutgers, The State University of New Jersey

• M.S., Computer Science

  Rutgers, The State University of New Jersey

• B.S., Computer Science

  Rutgers, The State University of New Jersey

Awards & honors

• NSF NRI grant
• NASA early career grant
• NSF grant
• two new grants
• NSF SA&S grant