Christoforos Kanellakis
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Christoforos Kanellakis has a total of 125 co-authors. Here are the top co-authors by number of shared publications:
- George Nikolakopoulos
Luleå University of Technology
25 shared publications George Nikolakopoulos
Lulea tekniska universitet Institutionen for system- och rymdteknik
10 shared publications- Ali-Akbar Agha-Mohammadi
Jet Propulsion Laboratory, California Institute of Technology, Pasadena, CA, USA
8 shared publications - Sina Sharif Mansouri
Luleå University of Technology
8 shared publications - Björn Lindqvist
Department of Computer Science, Electrical and Space Engineering, Lule University of Technology, Lule, Sweden
7 shared publications - Petros Karvelis
University of Ioannina
6 shared publications
Latest Publications
- 29 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Field Robotics
- Vol. 3, 364-385
xFLIE: Leveraging Actionable Hierarchical Scene Representation for Autonomous Semantic-Aware Inspection Missions
We present a novel architecture aimed at the incremental construction and exploitation of a hierarchical 3D scene graph representation during semantic-aware inspection missions. Inspection planning, particularly for distributed targets in previously unseen environments, presents an opportunity to exploit the semantic structure of the scene during reasoning, navigation, and scene understanding. Motivated by this, we propose the 3D Layered Semantic Graph (3DLSG), a hierarchical inspection scene graph constructed incrementally and organized into abstraction layers that support planning demands in real time. To address the task of semantic-aware inspection, we propose a mission framework, termed Enhanced First-Look Inspect Explore (xFLIE), that tightly couples the 3DLSG with an inspection planner. We assess performance through simulations and experimental trials, evaluating target selection, path planning, and semantic navigation tasks over the 3DLSG model. The scenarios presented are diverse, ranging from city-scale, distributed targets in simulated worlds to solitary infrastructure targets, as well as outdoor and subterranean environment deployments onboard a quadrupedal robot. The proposed method successfully demonstrates incremental construction and planning over the 3DLSG representation to meet mission objectives. Furthermore, the framework demonstrates successful semantic navigation tasks over the structured interface at the end of inspection missions. Finally, we report multiple orders of magnitude reduction in path-planning time compared to conventional volumetric-map-based methods over various environment scales, demonstrating the planning efficiency and scalability of the proposed approach.
- 29 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Field Robotics
- Vol. 3, 364-385
xFLIE: Leveraging Actionable Hierarchical Scene Representation for Autonomous Semantic-Aware Inspection Missions
We present a novel architecture aimed at the incremental construction and exploitation of a hierarchical 3D scene graph representation during semantic-aware inspection missions. Inspection planning, particularly for distributed targets in previously unseen environments, presents an opportunity to exploit the semantic structure of the scene during reasoning, navigation, and scene understanding. Motivated by this, we propose the 3D Layered Semantic Graph (3DLSG), a hierarchical inspection scene graph constructed incrementally and organized into abstraction layers that support planning demands in real time. To address the task of semantic-aware inspection, we propose a mission framework, termed Enhanced First-Look Inspect Explore (xFLIE), that tightly couples the 3DLSG with an inspection planner. We assess performance through simulations and experimental trials, evaluating target selection, path planning, and semantic navigation tasks over the 3DLSG model. The scenarios presented are diverse, ranging from city-scale, distributed targets in simulated worlds to solitary infrastructure targets, as well as outdoor and subterranean environment deployments onboard a quadrupedal robot. The proposed method successfully demonstrates incremental construction and planning over the 3DLSG representation to meet mission objectives. Furthermore, the framework demonstrates successful semantic navigation tasks over the structured interface at the end of inspection missions. Finally, we report multiple orders of magnitude reduction in path-planning time compared to conventional volumetric-map-based methods over various environment scales, demonstrating the planning efficiency and scalability of the proposed approach.
- Open Access
- 13 April 2026
- Published by Springer Nature in International Journal of Control, Automation, and Systems
- Vol. 24 (5) , 1143-1155
Coordinated Task Assignment and Path Planning with Trajectory Optimization for Multi-agent Systems
In this paper, we propose a holistic method for coordinated task assignment and trajectory generation for multi-agent systems in a known environment. First, we propose CBS-TS that generates conflict-free paths for each robot, while ensuring all the goal locations are visited. CBS-TS conducts the best-first search over a conflict forest, which is guaranteed to be optimal and complete. Then, the resulting paths are optimized to dynamically feasible trajectories. Through optimization constraints, the smoothed trajectory remains conflict-free and ensures all goal locations are precisely visited. We provide extensive simulation results to analyze the computational efficiency of the proposed algorithm and conduct physical experiments with heterogeneous robots to demonstrate the feasibility of generated trajectories.
- 13 April 2026
- Published by Springer Nature in International Journal of Control, Automation, and Systems
- Vol. 24 (5) , 1143-1155
Open AccessCoordinated Task Assignment and Path Planning with Trajectory Optimization for Multi-agent Systems
In this paper, we propose a holistic method for coordinated task assignment and trajectory generation for multi-agent systems in a known environment. First, we propose CBS-TS that generates conflict-free paths for each robot, while ensuring all the goal locations are visited. CBS-TS conducts the best-first search over a conflict forest, which is guaranteed to be optimal and complete. Then, the resulting paths are optimized to dynamically feasible trajectories. Through optimization constraints, the smoothed trajectory remains conflict-free and ensures all goal locations are precisely visited. We provide extensive simulation results to analyze the computational efficiency of the proposed algorithm and conduct physical experiments with heterogeneous robots to demonstrate the feasibility of generated trajectories.
- 24 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 11 (1) , 738-745
A Minimal Subset Approach for Informed Keyframe Sampling in Large-Scale SLAM
Typical LiDAR SLAM architectures feature a front-end for odometry estimation and a back-end for refining and optimizing the trajectory and map, commonly through loop closures. However, loop closure detection in large-scale missions presents significant computational challenges due to the need to identify, verify, and process numerous candidate pairs for pose graph optimization. Keyframe sampling bridges the front-end and back-end by selecting frames for storing and processing during global optimization. This article proposes an online keyframe sampling approach that constructs the pose graph using the most impactful keyframes for loop closure. We introduce the Minimal Subset Approach (MSA), which optimizes two key objectives: redundancy minimization and information preservation, implemented within a sliding window framework. By operating in the feature space rather than 3-D space, MSA efficiently reduces redundant keyframes while retaining essential information. Evaluations on diverse public datasets show that the proposed approach outperforms naive methods in reducing false positive rates in place recognition, while delivering superior ATE and RPE in metric localization, without the need for manual parameter tuning. Additionally, MSA demonstrates efficiency and scalability by reducing memory usage and computational overhead during loop closure detection and pose graph optimization.
- 24 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 11 (1) , 738-745
A Minimal Subset Approach for Informed Keyframe Sampling in Large-Scale SLAM
Typical LiDAR SLAM architectures feature a front-end for odometry estimation and a back-end for refining and optimizing the trajectory and map, commonly through loop closures. However, loop closure detection in large-scale missions presents significant computational challenges due to the need to identify, verify, and process numerous candidate pairs for pose graph optimization. Keyframe sampling bridges the front-end and back-end by selecting frames for storing and processing during global optimization. This article proposes an online keyframe sampling approach that constructs the pose graph using the most impactful keyframes for loop closure. We introduce the Minimal Subset Approach (MSA), which optimizes two key objectives: redundancy minimization and information preservation, implemented within a sliding window framework. By operating in the feature space rather than 3-D space, MSA efficiently reduces redundant keyframes while retaining essential information. Evaluations on diverse public datasets show that the proposed approach outperforms naive methods in reducing false positive rates in place recognition, while delivering superior ATE and RPE in metric localization, without the need for manual parameter tuning. Additionally, MSA demonstrates efficiency and scalability by reducing memory usage and computational overhead during loop closure detection and pose graph optimization.
- 17 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 10 (12) , 12477-12484
Have We Scene It All? Scene Graph-Aware Deep Point Cloud Compression
Efficient transmission of 3D point cloud data is critical for advanced perception in centralized and decentralized multi-agent robotic systems, especially nowadays with the growing reliance on edge and cloud-based processing. However, the large and complex nature of point clouds creates challenges under bandwidth constraints and intermittent connectivity, often degrading system performance. We propose a deep compression framework based on semantic scene graphs. The method decomposes point clouds into semantically coherent patches and encodes them into compact latent representations with semantic-aware encoders conditioned by Feature-wise Linear Modulation (FiLM). A folding-based decoder, guided by latent features and graph node attributes, enables structurally accurate reconstruction. Experiments on the SemanticKITTI and nuScenes datasets show that the framework achieves state-of-the-art compression rates, reducing data size by up to 98% while preserving both structural and semantic fidelity. In addition, it supports downstream applications such as multi-robot pose graph optimization and map merging, achieving trajectory accuracy and map alignment comparable to those obtained with raw LiDAR scans.
- 17 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 10 (12) , 12477-12484
Have We Scene It All? Scene Graph-Aware Deep Point Cloud Compression
Efficient transmission of 3D point cloud data is critical for advanced perception in centralized and decentralized multi-agent robotic systems, especially nowadays with the growing reliance on edge and cloud-based processing. However, the large and complex nature of point clouds creates challenges under bandwidth constraints and intermittent connectivity, often degrading system performance. We propose a deep compression framework based on semantic scene graphs. The method decomposes point clouds into semantically coherent patches and encodes them into compact latent representations with semantic-aware encoders conditioned by Feature-wise Linear Modulation (FiLM). A folding-based decoder, guided by latent features and graph node attributes, enables structurally accurate reconstruction. Experiments on the SemanticKITTI and nuScenes datasets show that the framework achieves state-of-the-art compression rates, reducing data size by up to 98% while preserving both structural and semantic fidelity. In addition, it supports downstream applications such as multi-robot pose graph optimization and map merging, achieving trajectory accuracy and map alignment comparable to those obtained with raw LiDAR scans.
- Open Access
- 9 March 2025
- Published by Qeios Ltd in Qeios Preprints
Balancing Accuracy and Efficiency for Large-Scale SLAM: A Minimal Subset Approach for Scalable Loop Closures
Typical LiDAR SLAM architectures feature a front-end for odometry estimation and a back-end for refining and optimizing the trajectory and map, commonly through loop closures. However, loop closure detection in large-scale missions presents significant computational challenges due to the need to identify, verify, and process numerous candidate pairs for pose graph optimization. Keyframe sampling bridges the front-end and back-end by selecting frames for storing and processing during global optimization. This article proposes an online keyframe sampling approach that constructs the pose graph using the most impactful keyframes for loop closure. We introduce the Minimal Subset Approach (MSA), which optimizes two key objectives: redundancy minimization and information preservation, implemented within a sliding window framework. By operating in the feature space rather than 3-D space, MSA efficiently reduces redundant keyframes while retaining essential information. In sum, evaluations on diverse public datasets show that the proposed approach outperforms naive methods in reducing false positive rates in place recognition, while delivering superior ATE and RPE in metric localization, without the need for manual parameter tuning. Additionally, MSA demonstrates efficiency and scalability by reducing memory usage and computational overhead during loop closure detection and pose graph optimization.
- 9 March 2025
- Published by Qeios Ltd in Qeios Preprints
Open AccessBalancing Accuracy and Efficiency for Large-Scale SLAM: A Minimal Subset Approach for Scalable Loop Closures
Typical LiDAR SLAM architectures feature a front-end for odometry estimation and a back-end for refining and optimizing the trajectory and map, commonly through loop closures. However, loop closure detection in large-scale missions presents significant computational challenges due to the need to identify, verify, and process numerous candidate pairs for pose graph optimization. Keyframe sampling bridges the front-end and back-end by selecting frames for storing and processing during global optimization. This article proposes an online keyframe sampling approach that constructs the pose graph using the most impactful keyframes for loop closure. We introduce the Minimal Subset Approach (MSA), which optimizes two key objectives: redundancy minimization and information preservation, implemented within a sliding window framework. By operating in the feature space rather than 3-D space, MSA efficiently reduces redundant keyframes while retaining essential information. In sum, evaluations on diverse public datasets show that the proposed approach outperforms naive methods in reducing false positive rates in place recognition, while delivering superior ATE and RPE in metric localization, without the need for manual parameter tuning. Additionally, MSA demonstrates efficiency and scalability by reducing memory usage and computational overhead during loop closure detection and pose graph optimization.
- Open Access
- 13 February 2025
- Published by Springer Nature in Journal of Intelligent & Robotic Systems
- Vol. 111 (1) , 1-12
Multi-agent Path Planning Based on Conflict-Based Search (CBS) Variations for Heterogeneous Robots
This article introduces a novel Multi-agent path planning scheme based on Conflict Based Search (CBS) for heterogeneous holonomic and non-holonomic agents, designated as Heterogeneous CBS (HCBS). The proposed methodology employs a hybrid $$A^*$$ algorithm for non-holonomic car-like robots and a conventional $$A^*$$ algorithm for holonomic robots. Following this, a body conflict detection strategy is utilized to construct the conflict tree, bridging the initial path planning with the resolution of conflicts among agents. Moreover, we present two variants of HCBS: the Enhanced Conflict-Based Search (EHCBS) and the Depth-First Conflict-Based Search (DFHCBS). We evaluate the efficacy of our proposed algorithms—HCBS, EHCBS, and DFHCBS—against a standard prioritized planning algorithm, focusing on success rates and computational efficiency in environments with varying numbers of agents and obstacles. The empirical results demonstrate that EHCBS exhibits superior computational efficiency in small, dense environments, while DFHCBS performs well in larger-scale environments. This highlights the adaptability of our proposed approaches in various settings, proving the computational advantage of EHCBS and DFHCBS over traditional methods.- 13 February 2025
- Published by Springer Nature in Journal of Intelligent & Robotic Systems
- Vol. 111 (1) , 1-12
Open AccessMulti-agent Path Planning Based on Conflict-Based Search (CBS) Variations for Heterogeneous Robots
This article introduces a novel Multi-agent path planning scheme based on Conflict Based Search (CBS) for heterogeneous holonomic and non-holonomic agents, designated as Heterogeneous CBS (HCBS). The proposed methodology employs a hybrid $$A^*$$ algorithm for non-holonomic car-like robots and a conventional $$A^*$$ algorithm for holonomic robots. Following this, a body conflict detection strategy is utilized to construct the conflict tree, bridging the initial path planning with the resolution of conflicts among agents. Moreover, we present two variants of HCBS: the Enhanced Conflict-Based Search (EHCBS) and the Depth-First Conflict-Based Search (DFHCBS). We evaluate the efficacy of our proposed algorithms—HCBS, EHCBS, and DFHCBS—against a standard prioritized planning algorithm, focusing on success rates and computational efficiency in environments with varying numbers of agents and obstacles. The empirical results demonstrate that EHCBS exhibits superior computational efficiency in small, dense environments, while DFHCBS performs well in larger-scale environments. This highlights the adaptability of our proposed approaches in various settings, proving the computational advantage of EHCBS and DFHCBS over traditional methods. - Open Access
- 16 January 2025
- Published by Wiley in Journal of Field Robotics
- Vol. 42 (5) , 2076-2094
Safety Inspections and Gas Monitoring in Hazardous Mining Areas Shortly After Blasting Using Autonomous UAVs
This article presents the first ever fully autonomous UAV (Unmanned Aerial Vehicle) mission to perform gas measurements after a real blast in an underground mine. The demonstration mission was deployed around 40 min after the blast took place, and as such realistic gas levels were measured. We also present multiple field robotics experiments in different mines detailing the development process. The presented novel autonomy stack, denoted as the Routine Inspection Autonomy (RIA) framework, combines a risk‐aware 3D path planning , with 3D LiDAR‐based global relocalization on a known map, and it is integrated on a custom hardware and a sensing stack with an onboard gas sensing device. In the presented framework, the autonomous UAV can be deployed in incredibly harsh conditions (dust, significant deformations of the map) shortly after blasting to perform inspections of lingering gases that present a significant safety risk to workers. We also present a change detection framework that can extract and visualize the areas that were changed in the blasting procedure, a critical parameter for planning the extraction of materials, and for updating existing mine maps. As will be demonstrated, the RIA stack can enable robust autonomy in harsh conditions, and provides reliable and safe navigation behavior for autonomous Routine Inspection missions.
- 16 January 2025
- Published by Wiley in Journal of Field Robotics
- Vol. 42 (5) , 2076-2094
Open AccessSafety Inspections and Gas Monitoring in Hazardous Mining Areas Shortly After Blasting Using Autonomous UAVs
This article presents the first ever fully autonomous UAV (Unmanned Aerial Vehicle) mission to perform gas measurements after a real blast in an underground mine. The demonstration mission was deployed around 40 min after the blast took place, and as such realistic gas levels were measured. We also present multiple field robotics experiments in different mines detailing the development process. The presented novel autonomy stack, denoted as the Routine Inspection Autonomy (RIA) framework, combines a risk‐aware 3D path planning , with 3D LiDAR‐based global relocalization on a known map, and it is integrated on a custom hardware and a sensing stack with an onboard gas sensing device. In the presented framework, the autonomous UAV can be deployed in incredibly harsh conditions (dust, significant deformations of the map) shortly after blasting to perform inspections of lingering gases that present a significant safety risk to workers. We also present a change detection framework that can extract and visualize the areas that were changed in the blasting procedure, a critical parameter for planning the extraction of materials, and for updating existing mine maps. As will be demonstrated, the RIA stack can enable robust autonomy in harsh conditions, and provides reliable and safe navigation behavior for autonomous Routine Inspection missions.
- Open Access
Investigating the Impact of Communication-Induced Action Space on Exploration of Unknown Environments with Decentralized Multi-Agent Reinforcement Learning
This paper introduces a novel enhancement to the Decentralized Multi-Agent Reinforcement Learning (D-MARL) exploration by proposing communication-induced action space to improve the mapping efficiency of unknown environments using homogeneous agents. Efficient exploration of large environments relies heavily on inter-agent communication as real-world scenarios are often constrained by data transmission limits, such as signal latency and bandwidth. Our proposed method optimizes each agent's policy using the heterogeneous-agent proximal policy optimization algorithm, allowing agents to autonomously decide whether to communicate or to explore, that is whether to share the locally collected maps or continue the exploration. We propose and compare multiple novel reward functions that integrate inter-agent communication and exploration, enhance mapping efficiency and robustness, and minimize exploration overlap. This article presents a framework developed in ROS2 to evaluate and validate the investigated architecture. Specifically, four TurtleBot3 Burgers have been deployed in a Gazebo-designed environment filled with obstacles to evaluate the efficacy of the trained policies in mapping the exploration arena.
Open AccessInvestigating the Impact of Communication-Induced Action Space on Exploration of Unknown Environments with Decentralized Multi-Agent Reinforcement Learning
This paper introduces a novel enhancement to the Decentralized Multi-Agent Reinforcement Learning (D-MARL) exploration by proposing communication-induced action space to improve the mapping efficiency of unknown environments using homogeneous agents. Efficient exploration of large environments relies heavily on inter-agent communication as real-world scenarios are often constrained by data transmission limits, such as signal latency and bandwidth. Our proposed method optimizes each agent's policy using the heterogeneous-agent proximal policy optimization algorithm, allowing agents to autonomously decide whether to communicate or to explore, that is whether to share the locally collected maps or continue the exploration. We propose and compare multiple novel reward functions that integrate inter-agent communication and exploration, enhance mapping efficiency and robustness, and minimize exploration overlap. This article presents a framework developed in ROS2 to evaluate and validate the investigated architecture. Specifically, four TurtleBot3 Burgers have been deployed in a Gazebo-designed environment filled with obstacles to evaluate the efficacy of the trained policies in mapping the exploration arena.
- 2 August 2024
- Published by Springer Nature in International Journal of Control, Automation, and Systems
- Vol. 22 (8) , 2537-2550
Cluster-based Multi-robot Task Assignment, Planning, and Control
- 2 August 2024
- Published by Springer Nature in International Journal of Control, Automation, and Systems
- Vol. 22 (8) , 2537-2550
Cluster-based Multi-robot Task Assignment, Planning, and Control
- Open Access
- 12 March 2024
- Published by Wiley
Safety Inspections and Gas Monitoring in Hazardous Mining Areas Shortly After Blasting Using Autonomous UAVs
This article presents the first ever fully autonomous UAV (Unmanned Aerial Vehicle) mission to perform gas measurements after a real blast in an underground mine. The demonstration mission was deployed around 40 minutes after the blast took place, and as such realistic gas levels were measured. We also present multiple field robotics experiments in different mines detailing the development process. The presented novel autonomy stack, denoted as the Routine Inspection Autonomy (RIA) framework, combines a risk-aware 3D path planning D + ∗ , with 3D LiDAR-based global relocalization on a known map, and it is integrated on a custom hardware and a sensing stack with an onboard gas sensing device. In the presented framework, the autonomous UAV can be deployed in incredibly harsh conditions (dust, significant deformations of the map) shortly after blasting to perform inspections of lingering gases that present a significant safety risk to workers. We also present a change detection framework that can extract and visualize the areas that were changed in the blasting procedure, a critical parameter for planning the extraction of materials, and for updating existing mine maps. As will be demonstrated, the RIA stack can enable robust autonomy in harsh conditions, and provides reliable and safe navigation behavior for autonomous Routine Inspection missions.
- 12 March 2024
- Published by Wiley
Open AccessSafety Inspections and Gas Monitoring in Hazardous Mining Areas Shortly After Blasting Using Autonomous UAVs
This article presents the first ever fully autonomous UAV (Unmanned Aerial Vehicle) mission to perform gas measurements after a real blast in an underground mine. The demonstration mission was deployed around 40 minutes after the blast took place, and as such realistic gas levels were measured. We also present multiple field robotics experiments in different mines detailing the development process. The presented novel autonomy stack, denoted as the Routine Inspection Autonomy (RIA) framework, combines a risk-aware 3D path planning D + ∗ , with 3D LiDAR-based global relocalization on a known map, and it is integrated on a custom hardware and a sensing stack with an onboard gas sensing device. In the presented framework, the autonomous UAV can be deployed in incredibly harsh conditions (dust, significant deformations of the map) shortly after blasting to perform inspections of lingering gases that present a significant safety risk to workers. We also present a change detection framework that can extract and visualize the areas that were changed in the blasting procedure, a critical parameter for planning the extraction of materials, and for updating existing mine maps. As will be demonstrated, the RIA stack can enable robust autonomy in harsh conditions, and provides reliable and safe navigation behavior for autonomous Routine Inspection missions.