Distributed Robot Intelligence Lab
Department of Artificial Intelligence, Korea University, Seoul, Korea
We are actively hiring M.S. Ph.D. Postdoc researcher.
Feel free to contant us to the following e-mail with your CV.
Development of algorithmic solutions for multi-robot systems and surgical robot platforms.

This work presents the curvature-continuous path planning of a car-like robot for its turning motion around an obstacle. For the smoothness of the path, we adopt a cubic parabola whose curvature increases proportional to the location of the robot from its initial pose. We define multi-stage path planning problems. In the base stage, we assume a fixed initial and a fixed target configuration of a robot in an SE(2) state space and present an analytic formula for the curvature-continuous path and its deterministic way of checking a collision with a polygonal obstacle. In the inductive stage, we move our focus to the closed-form expression of a distance-optimal, collision-free path under flexible target orientation. In both stages, we provide in-depth performance analysis and validations with various case studies. The resulting paths in the base stage comply curvature-continuity constraint (less than 0.2 rad/m curvature changes) with 5.5 ms computation time, which is suitable for real-time applications. Regarding the inductive stage, the distance-optimal paths formed by our method satisfy the curvature-continuity constraint (0.2 rad/m maximum curvature) and consume less time (maximum 2.34 ms) while still showing similar path lengths (average 23.8 m), compared to those by an existing method (
rad/m maximum curvature, 110.7 ms maximum computation time, and 24.6 m average path length).

Local path planning scheme for car-like robots’ shortest turning motion using geometric analysis

This study presents a
cohesive configuration controller
for distributed space coverage by a swarm of robots. The goal is to build a dense, convex network that is robust against disconnection while robots are flocking with only incomplete knowledge about the network. The controller is an integrated framework of two different algorithms. First, we present a
boundary force
algorithm: physics-based swarm intelligence that borrows the concept of surface tension force between liquid molecules. The combination of such a force with conventional flocking produces a convex and dense configuration without knowledge of the complete geometry of a robot network. Second, robots distributively determine when a configuration is on the verge of disconnection by identifying a local articulation point—a region where the removal of a single robot will change the local topology. When such a point is detected, robots switch their behavior to
clustering
, which aggregates them around the vulnerable region to remove every articulation point and retain a connected configuration. Finally, we introduced an index that objectively represents the level of risk of a robot configuration against the massive fragmentation, called
vulnerability index
. We provide theoretical performance analyses of each algorithm and validate the results with simulations and experiments using a set of low-cost robots.

Distributed cohesive configuration controller for a swarm with low‐cost platforms

This work presents a deformable configuration controller—a fully distributed algorithm that enables a swarm of robots to avoid an obstacle while maintaining network connectivity. We assume a group of robots flocking in an unknown environment, each of which has only incomplete knowledge of the geometry without a map, a shared coordinate, or the use of a centralized control scheme. Instead, the controller requires only local information about the area around individual robots. We devise a phase transition machine, which designs overall obstacle avoidance procedures in a fully distributed way. Robots in collision with an obstacle distributively measure the topology of the sensor network formed by the robots in order to estimate the shape of the obstacle, and choose a motion model, either obstacle-detouring or bouncing-off, each of which deforms the network to avoid an obstacle without knowledge of the geometry around the obstacle. The robots then sense the maximum tree angle, which detects the straightness of a configuration to ensure the completion of the obstacle avoidance procedure, and perform flocking with a modified heading consensus to reconstruct a volumed network with their original headings. We provide theoretical performance analyses of the controller. We also validate the theoretical results by multiple simulations with a swarm with various population sizes.

Distributed deformable configuration control for multi-robot systems with low-cost platforms

: This paper presents a forward kinematic model of a wire-driven surgical robot arm with an articulated joint structure and path generation algorithms with solutions of inverse kinematics. The proposed methods were applied to a wire-driven surgical robot for single-port surgery. This robot has a snake-like robotic arm with double segments to fit the working space in a single port and a joint structure to secure stiffness. The accuracy of the model is highly important because small surgical robot arms are usually controlled by open-loop control. A curvature model is widely used to describe and control a continuum robotic body. However, the model is quite different from a continuum robotic arm with a joint structure and can lead to slack of the driving wires or decreased stiffness of the joints. An accurate forward kinematic model was derived to fit the actual hardware structure via the frame transformation method. An inverse kinematic model from the joint space to the wire-length space was determined from an asymmetric model for the joint structure as opposed to a symmetric curvature model. The path generation algorithm has to generate a command to send to each actuator in open-loop control. Two real-time path generation algorithms that solve for inverse kinematics from the task space to the joint space were designed and compared using simulations and experiments. One of the algorithms is an optimization method with sequential quadratic programming (SQP), and the other uses differential kinematics with a PID (Proportional-Integral-Derivative) control algorithm. The strengths and weaknesses of each algorithm are discussed.

Kinematic model and real-time path generator for a wire-driven surgical robot arm with articulated joint structure

: We give lower bounds for various natural node- and edge-based local strategies for exploring a graph. We consider this problem both in the setting of an arbitrary graph as well as the abstraction of a geometric exploration of a space by a robot, both of which have been extensively studied. We consider local exploration policies that use time-of-last-visit or alternatively least-frequently-visited local greedy strategies to select the next step in the exploration path. Both of these strategies were previously considered by Cooper et al. (2011) for a scenario in which counters for the last visit or visit frequency are attached to the edges. In this work we consider the case in which the counters are associated with the nodes, which for the case of dual graphs of geometric spaces could be argued to be intuitively more natural and likely more efficient. Surprisingly, these alternate strategies give worst-case superpolynomial/exponential time for exploration, whereas the least-frequently-visited strategy for edges has a polynomially bounded exploration time, as shown by Cooper et al. (2011).

Lower Bounds for Graph Exploration Using Local Policies

: We present a fundamental framework for organizing exploration, coverage, and surveillance by a swarm of robots with limited individual capabilities, based on triangulating an unknown environment with a multi-robot system. Locally, an individual triangle is easy for a single robot to manage and covers a small area; globally, the topology of the triangulation approximately captures the geometry of the entire environment. Combined, a multi-robot system can explore, map, navigate, and patrol. Algorithms can store information in triangles that the robots can read and write as they run their algorithms. This creates a physical data structure (PDS) that is both robust and versatile.
We study distributed approaches to triangulating an unknown, two-dimensional Euclidean space using a multi-robot network. The resulting PDS is a compact representation of the workspace, contains distributed knowledge of each triangle, encodes the dual graph of the triangulation, and supports reads and writes of auxiliary data. The ability to store and process this auxiliary information enables the simple robots to solve complex problems. We develop distributed algorithms for dual-graph navigation, patrolling, construction of a topological Voronoi tessellation, and location of the geodesic centers in non-convex regions. We provide theoretical performance guarantees for the quality of constructed triangulation and the connectivity of a dual graph in the triangulation. In addition, we show that the path lengths of the physical navigation are within a constant factor of the shortest-path Euclidean distance. We validate these theoretical results with simulations and experiments with a dozen or more robots.

Structured triangulation in multi-robot systems: Coverage, patrolling, voronoi partitions, and geodesic centers

In this paper, we present deformable configuration control — a fully distributed algorithm that allows multiple robots to deform their configuration to avoid various shapes of obstacles while maintaining connectivity. Robots contacted with an obstacle first estimate the width of an obstacle by sharing bumped status of individual robots, and choose an appropriate obstacle avoidance scenarios between obstacle detouring and bouncing off a wall. Second, for both scenarios, robots switch their motion model to a parent following motion to avoid the obstacle. Finally, robots keep sensing the maximum tree angle to estimate whether they are completely escaped from the obstacle, and return to flock formation motion model. We provide theoretical analysis about maintaining connectivity while robots are avoiding an obstacle. Simulation results show a group of 36 robots successfully avoid three different kinds of obstacles including 1) a small bar, 2) a narrow corridor, and 3) a large wall while maintaining connectivity.

Distributed deformable configuration control for Multi-Robot systems

We present and analyze methods for patrolling and surveillance in an environment with a distributed swarm of robots with limited capabilities. Our approach is based on a distributed triangulation of the work space, in which a set of p stationary sensors provides coverage control; in addition, there are r mobile robots that can move between the sensors. Building on our prior work on structured exploration of unknown spaces with multi-robot systems, we can make use of a triangulation that is constructed in a distributed fashion and guarantees good local navigation properties, even when sensors and robots have very limited capabilities.

Local policies for efficiently patrolling a triangulated region by a robot swarm

Positioning a group of robots at the center of their geodesic voronoi cells minimizes the worst-case response time for any robot to arrive at an exogenous event in the workspace. We construct these cells in a distributed fashion, building on our prior work on triangulating unknown spaces with multi-robot systems. This produces a physical data structure - a set of triangles formed by the positions of the robots that can be used to perform coverage control. This paper presents: 1) A discrete approximation of the geodesic Voronoi cell using the multi-robot triangulation. We call this a topological Voronoi cell, and show that it can be computed efficiently in a distributed fashion and with theoretical guarantees compared to continuous version. 2) A local motion controller to guide navigating robots to the centroid of their topological Voronoi cell. This controller uses bounded communications with a fixed constant, but can produce local extrema that trap navigating robots away from the optimal position. 3) An enhanced local controller using navigation agents to help guide the navigating robot to the optimal position in its Voronoi cell. It also uses bounded communications, but with a constant that can be tuned to trade communications bandwidth for increased accuracy. 4) Hardware experiments that compute the topological Voronoi cell on a group of 14 robots, simulation results that demonstrate local extrema, and the effectiveness of the virtual navigation agents, and simulation results comparing the performance of the patrolling algorithm using and not using topological Voronoi cells.

Geodesic topological voronoi tessellations in triangulated environments with multi-robot systems

In this paper, we present flocking with cohesive configuration control — motion controllers that allow multiple robots to move through the environment as a coherent group while maintaining connectivity and density invariants. We start with a flocking controller from the literature. First, we produce a boundary force on robots that are on the internal and external boundaries of the configuration. This removes concave regions of the boundary, producing a convex configuration with uniform density. Second, we solve interstitial lattice errors caused by robots clumping too close together by moving them towards the boundary with a clump remover algorithm. Finally, we determine when a configuration is on the verge of disconnecting by identifying local articulation points; regions where the removal of a single robot will change the local topology. When one is detected, we switch modes to a clustering algorithm that draws robots to the vulnerable region. The combination of these algorithms produces a cohesive configuration controller. We verify our resulting controller with simulations from random initial conditions and selected extreme cases. Simulation results show the controller successfully forms a configuration with natural resting density in twelve of trials and maintains connectivity in twelve trials. We also provide real-world experiments to show that proposed algorithms work under low-resolution sensor platforms.

Distributed cohesive configuration control for swarm robots with boundary information and network sensing

This paper presents a distributed approach for exploring and triangulating an unknown region using a multirobot system. The resulting triangulation is a physical data structure that is a: compact representation of the workspace, contains distributed knowledge of each triangle, builds the dual graph of the triangulation, and supports reads and writes of auxiliary data. Our algorithm builds a triangulation in a closed two-dimensional Euclidean environment, starting from a single location. It provides coverage with a breadth-first search pattern and completeness guarantees. We show that the computational and communication requirements to build and maintain the triangulation and its dual graph are small. We then present a physical navigation algorithm that uses the dual graph, and show that the resulting path lengths are within a constant factor of the shortest-path Euclidean distance. Finally, we validate our theoretical results with experiments on triangulating a region with a system of low-cost robots. Analysis of the resulting triangulation shows that most of the triangles are of high quality, and cover a large area. Implementation of the triangulation, dual graph, and navigation all use communication messages of fixed size, and are a practical solution for large populations of low-cost robots.

Exploration via structured triangulation by a multi-robot system with bearing-only low-resolution sensors

Patrolling a region with a structured swarm of robots with limited individual capabilities

In recent years, the field of robotics has seen two diverging trends. One has been to achieve progress by increasing the capabilities of individual robots, keeping the cost of state-of-art machines relatively high. An opposite direction has been to develop simpler and cheaper platforms, at the expense of reducing the capabilities per robot. The latter raises new challenges for developing new principles and algorithms, such as coordinating many robots with limited capabilities into a swarm that can carry out difficult tasks, for example, exploration, surveillance, and guidance. In this video, we show a recent collaboration between theory and practice of swarm robotics. We consider online problems related to exploring and surveying a region by a swarm of robots with limited communication range.

Triangulating unknown environments using robot swarms

This paper deals with a path planning problem for turning motion of a car-like vehicle. We propose a turning method which finds a curvature continuous optimal path between two positions for a car-like vehicle.

Local path planning scheme for car-like vehicle's shortest turning motion using geometric analysis

Bezier curve based path planning for a car-like robot

MASTER CONTROL SYSTEMS FOR ROBOTIC SURGICAL SYSTEMS

DISPLAY SYSTEMS FOR ROBOTIC SURGICAL SYSTEMS

SAFETY HAND SENSOR SYSTEMS FOR ROBOTIC SURGICAL SYSTEM

SELF MOVABLE CRANE SYSTEM WITH A BOOM

Robotic technologies for the automatic assemble of massive beams in high-rise building

A robust localization algorithm in topological maps with dynamic noises

Distributed space coverage for exploration, localization, and navigation in unknown environments

Self movable crane system with a boom

Novel index for the best node selection problem and enhanced technique for the node's state estimation

James McLurkin

Sándor P. Fekete

Aaron T. Becker

Alexander Kröller

Alejandro Lopez-Ortiz

Daniela Maftuleac

Aditya Kumar Akash

Tae-Koo Kang

Michael Seokyoung Han

Sangrok Jin

Jaeyeon Lee

Daehie Hong

Changjoo Nam

sungon lee

Wan Kyun Chung

Taeho Jang

Suyong Yeon

Tae-Hoon Kim

Seoungkyou Lee

We present a fundamental framework for organizing exploration, coverage, and surveillance by a swarm of robots with limited individual capabilities, based on triangulating an unknown environment with a multi-robot system. Locally, an individual triangle is easy for a single robot to manage and covers a small area; globally, the topology of the triangulation approximately captures the geometry of the entire environment. Combined, a multi-robot system can explore, map, navigate, and patrol. Algorithms can store information in triangles that the robots can read and write as they run their algorithms. This creates a physical data structure (PDS) that is both robust and versatile. We study distributed approaches to triangulating an unknown, two-dimensional Euclidean space using a multi-robot network. The resulting PDS is a compact representation of the workspace, contains distributed knowledge of each triangle …

This paper presents a forward kinematic model of a wire-driven surgical robot arm with an articulated joint structure and path generation algorithms with solutions of inverse kinematics. The proposed methods were applied to a wire-driven surgical robot for single-port surgery. This robot has a snake-like robotic arm with double segments to fit the working space in a single port and a joint structure to secure stiffness. The accuracy of the model is highly important because small surgical robot arms are usually controlled by open-loop control. A curvature model is widely used to describe and control a continuum robotic body. However, the model is quite different from a continuum robotic arm with a joint structure and can lead to slack of the driving wires or decreased stiffness of the joints. An accurate forward kinematic model was derived to fit the actual hardware structure via the frame transformation method. An inverse kinematic model from the joint space to the wire-length space was determined from an asymmetric model for the joint structure as opposed to a symmetric curvature model. The path generation algorithm has to generate a command to send to each actuator in open-loop control. Two real-time path generation algorithms that solve for inverse kinematics from the task space to the joint space were designed and compared using simulations and experiments. One of the algorithms is an optimization method with sequential quadratic programming (SQP), and the other uses differential kinematics with a PID (Proportional-Integral-Derivative) control algorithm. The strengths and weaknesses of each algorithm are discussed.

In recent years, the field of robotics has seen two diverging trends. One has been to achieve progress by increasing the capabilities of individual robots, keeping the cost of state-of-art machines relatively high. An opposite direction has been to develop simpler and cheaper platforms, at the expense of reducing the capabilities per robot. The latter raises new challenges for developing new principles and algorithms, such as coordinating many robots with limited capabilities into a swarm that can carry out difficult tasks, for example, exploration, surveillance, and guidance. In this video, we show a recent collaboration between theory and practice of swarm robotics. We consider online problems related to exploring and surveying a region by a swarm of robots with limited communication range. The minimum relay triangulation problem (MRTP) asks for placing a minimum number of robots, such that their communication …

This paper presents a distributed approach for exploring and triangulating an unknown region using a multirobot system. The resulting triangulation is a physical data structure that is a: compact representation of the workspace, contains distributed knowledge of each triangle, builds the dual graph of the triangulation, and supports reads and writes of auxiliary data. Our algorithm builds a triangulation in a closed two-dimensional Euclidean environment, starting from a single location. It provides coverage with a breadth-first search pattern and completeness guarantees. We show that the computational and communication requirements to build and maintain the triangulation and its dual graph are small. We then present a physical navigation algorithm that uses the dual graph, and show that the resulting path lengths are within a constant factor of the shortest-path Euclidean distance. Finally, we validate our theoretical …

In this paper, we introduce a new technique for automatic construction of steel frames in high-rise buildings. Basically, we combine advanced robotic technologies to building construction techniques. Four main topics will be developed such as: 1) Planning and synthesis of automatic construction system(ACS), 2) Development of construction factory(CF) system with climbing oil-pressured robot, 3) Core techniques for automatic assembly for steel frames, and 4) Intelligent resource management system. We expect that this new technique will increase the construction efficiency and will alleviate the manpower shortage problem in the aging society. For the development of the proposed system, two main ideas will be suggested. The first idea is to utilize a transportation system for the robot. One of the main problems of the automatic construction is that the size of the construction factory is very huge while that of the robot …

In this paper, we present flocking with cohesive configuration control — motion controllers that allow multiple robots to move through the environment as a coherent group while maintaining connectivity and density invariants. We start with a flocking controller from the literature. First, we produce a boundary force on robots that are on the internal and external boundaries of the configuration. This removes concave regions of the boundary, producing a convex configuration with uniform density. Second, we solve interstitial lattice errors caused by robots clumping too close together by moving them towards the boundary with a clump remover algorithm. Finally, we determine when a configuration is on the verge of disconnecting by identifying local articulation points; regions where the removal of a single robot will change the local topology. When one is detected, we switch modes to a clustering algorithm that draws …

This study presents a cohesive configuration controller for distributed space coverage by a swarm of robots. The goal is to build a dense, convex network that is robust against disconnection while robots are flocking with only incomplete knowledge about the network. The controller is an integrated framework of two different algorithms. First, we present a boundary force algorithm: physics‐based swarm intelligence that borrows the concept of surface tension force between liquid molecules. The combination of such a force with conventional flocking produces a convex and dense configuration without knowledge of the complete geometry of a robot network. Second, robots distributively determine when a configuration is on the verge of disconnection by identifying a local articulation point—a region where the removal of a single robot will change the local topology. When such a point is detected, robots switch their …

Purpose – The paper's purpose is to propose a localization algorithm for topological maps constituted by nodes and edges in a graph form. The focus is to develop a robust localization algorithm that works well even under various dynamic noises. Design/methodology/approach – For robust localization, the authors propose an algorithm which utilizes all available data such as node information, sensor measurements at the current time step (which are used in previous algorithms) and edge information, and sensor measurements at previous time steps (which have not been considered in other papers). Also, the algorithm estimates a robot's location in a multi‐modal manner which increases its robustness. Findings – Findings show that the proposed algorithm works well in topological maps with various dynamics which are induced by the moving objects in the map and measurement noises from cheap sensors …

This work presents a deformable configuration controller —a fully distributed algorithm that enables a swarm of robots to avoid an obstacle while maintaining network connectivity. We assume a group of robots flocking in an unknown environment, each of which has only incomplete knowledge of the geometry without a map, a shared coordinate, or the use of a centralized control scheme. Instead, the controller requires only local information about the area around individual robots. We devise a phase transition machine, which designs overall obstacle avoidance procedures in a fully distributed way. Robots in collision with an obstacle distributively measure the topology of the sensor network formed by the robots in order to estimate the shape of the obstacle, and choose a motion model, either obstacle-detouring or bouncing-off , each of which deforms the network to avoid an obstacle without knowledge of the …

In this paper, we present deformable configuration control — a fully distributed algorithm that allows multiple robots to deform their configuration to avoid various shapes of obstacles while maintaining connectivity. Robots contacted with an obstacle first estimate the width of an obstacle by sharing bumped status of individual robots, and choose an appropriate obstacle avoidance scenarios between obstacle detouring and bouncing off a wall. Second, for both scenarios, robots switch their motion model to a parent following motion to avoid the obstacle. Finally, robots keep sensing the maximum tree angle to estimate whether they are completely escaped from the obstacle, and return to flock formation motion model. We provide theoretical analysis about maintaining connectivity while robots are avoiding an obstacle. Simulation results show a group of 36 robots successfully avoid three different kinds of obstacles …

Positioning a group of robots at the center of their geodesic voronoi cells minimizes the worst-case response time for any robot to arrive at an exogenous event in the workspace. We construct these cells in a distributed fashion, building on our prior work on triangulating unknown spaces with multi-robot systems. This produces a physical data structure - a set of triangles formed by the positions of the robots that can be used to perform coverage control. This paper presents: 1) A discrete approximation of the geodesic Voronoi cell using the multi-robot triangulation. We call this a topological Voronoi cell, and show that it can be computed efficiently in a distributed fashion and with theoretical guarantees compared to continuous version. 2) A local motion controller to guide navigating robots to the centroid of their topological Voronoi cell. This controller uses bounded communications with a fixed constant, but can produce …

Many tasks, such as search and rescue, exploration and mapping, security and surveil-lance are suited for mobile robots. These tasks require the population to spread out over a large environment, where the sensing and communicating capacity of an individual robot might be too small to cover the entire environment. This thesis presents approaches for cooperative coverage tasks by large populations of robots to overcome the limitation of a single robot. Not only can a multi-robot system accomplish the coverage task far more efficiently than an individual robot, but also it is more reliable against individual hardware failure.

We give lower bounds for various natural node- and edge-based local strategies for exploring a graph. We consider this problem both in the setting of an arbitrary graph as well as the abstraction of a geometric exploration of a space by a robot, both of which have been extensively studied. We consider local exploration policies that use time-of-last-visit or alternatively least-frequently-visited local greedy strategies to select the next step in the exploration path. Both of these strategies were previously considered by Cooper et al. (2011) for a scenario in which counters for the last visit or visit frequency are attached to the edges. In this work we consider the case in which the counters are associated with the nodes, which for the case of dual graphs of geometric spaces could be argued to be intuitively more natural and likely more efficient. Surprisingly, these alternate strategies give worst-case superpolynomial …

This work presents the curvature-continuous path planning of a car-like robot for its turning motion around an obstacle. For the smoothness of the path, we adopt a cubic parabola whose curvature increases proportional to the location of the robot from its initial pose. We define multi-stage path planning problems. In the base stage, we assume a fixed initial and a fixed target configuration of a robot in an SE (2) state space and present an analytic formula for the curvature-continuous path and its deterministic way of checking a collision with a polygonal obstacle. In the inductive stage, we move our focus to the closed-form expression of a distance-optimal, collision-free path under flexible target orientation. In both stages, we provide in-depth performance analysis and validations with various case studies. The resulting paths in the base stage comply curvature-continuity constraint (less than 0.2 rad/m curvature changes …

A self movable boom system is provided. The self movable boom system include: a boom disposed on a plane perpen dicular to a building clamp structure; and a moving unit apparatus including a circumferential moving unit which is disposed between the boom and the building clamp structure to move the boom on a plane perpendicular to the building clamp structure, a lifting-up unit of which one end is disposed toward the circumferential moving unit and of which other end is disposed toward the building clamp structure to move the boom along a longitudinal direction of the building clamp structure, and a boom moving unit which moves an object along the longitudinal direction of the building clamp struc ture and along a longitudinal direction of the boom.

The best node selection problem, that distinguishes a node with the best state among multiply connected nodes, is one of the fundamental problem in robotics. However, a systematic solution has not been proposed by its ambiguity characteristics. To make the problem tractable, we reduce the scope of the original problem. Then, we suggest a novel index that systematically judges a required time step needed for a node to be the best. Furthermore, we suggest a new estimation technique that outperforms than previous approaches by 4.94 times in its settling time.

Electrical Engineering and Computer Science

DRI LAB

교수님 소개

이승규

연구실 소개

연구실 키워드

알럼나이가 간 회사

연구실 지원 방법

대우 조건

연도별 논문 인용수

저널 & 학회 논문 출판 수

연구실 논문 목록

Local path planning scheme for car-like robots’ shortest turning motion using geometric analysis

Distributed cohesive configuration controller for a swarm with low‐cost platforms

Distributed deformable configuration control for multi-robot systems with low-cost platforms

연구실 보유 특허

대학별 입시끈

우리 연구실 모집

교수님 소개

이승규

연구실 키워드

알럼나이가 간 회사

연구실 지원 방법

대우 조건

연도별 논문 인용수

저널 & 학회 논문 출판 수

연구실 논문 목록

Local path planning scheme for car-like robots’ shortest turning motion using geometric analysis

Distributed cohesive configuration controller for a swarm with low‐cost platforms

Distributed deformable configuration control for multi-robot systems with low-cost platforms

연구실 보유 특허

최근 3년간 연구실적 높은 연구실

대학별 입시끈

우리 연구실 모집