Alfred Marcel Bruckstein
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Alfred Marcel Bruckstein has a total of 77 co-authors. Here are the top co-authors by number of shared publications:
Michael Amir
Department of Computer Science Technion -Israel Institute of Technology 3200000 Haifa Israel
5 shared publications- Ron Kimmel
Technion - Israel institute of Technology
5 shared publications - Yehuda Dar
Rice University
5 shared publications - Roee Mordechai Francos
Faculty of Computer Science, TechnionIsrael Institute of Technology, Haifa, Israel
4 shared publications - Alex Pentland
Institute for Data, Systems, and Society, Massachusetts Institute of Technology, Cambridge, USA
3 shared publications - Ariel Barel
Henry and Marilyn Taub Faculty of Computer Science, Technion Israel Institute of Technology, Haifa, Israel
3 shared publications
Latest Publications
- Open Access
- 4 October 2026
- Published by Springer Nature in Artificial Life and Robotics
- p. 1-11
Sensor to pixels: swarm gathering via image-based reinforcement learning
This study highlights the potential of image-based reinforcement learning methods for addressing swarm-related tasks. In multi-agent reinforcement learning, effective policy learning depends on how agents sense, interpret, and process local inputs. Traditional approaches often rely on handcrafted feature extraction or raw vector-based representations, which limit the scalability and efficiency of learned policies concerning input order and size. In this work, we propose an image-based reinforcement learning method for decentralized control of a multi-agent system, where observations are encoded as structured visual inputs that neural networks can process, extracting spatial features and producing decentralized motion control rules. We evaluate our approach on a multi-agent gathering task of agents with limited-range and bearing-only sensing that aim to preserve visibility-graph connectivity during the aggregation. The algorithm’s performance is evaluated against two benchmarks: an analytical solution proposed by Bellaiche and Bruckstein, which ensures gathering success, but progresses slowly, and VariAntNet , a neural network-based framework that gathers much faster, but shows moderate success rates in adverse initial agent configurations. Our method achieves high gathering success, with a speed nearly matching that of VariAntNet . In certain scenarios, it offers a viable alternative to existing approaches.
- 4 October 2026
- Published by Springer Nature in Artificial Life and Robotics
- p. 1-11
Open AccessSensor to pixels: swarm gathering via image-based reinforcement learning
This study highlights the potential of image-based reinforcement learning methods for addressing swarm-related tasks. In multi-agent reinforcement learning, effective policy learning depends on how agents sense, interpret, and process local inputs. Traditional approaches often rely on handcrafted feature extraction or raw vector-based representations, which limit the scalability and efficiency of learned policies concerning input order and size. In this work, we propose an image-based reinforcement learning method for decentralized control of a multi-agent system, where observations are encoded as structured visual inputs that neural networks can process, extracting spatial features and producing decentralized motion control rules. We evaluate our approach on a multi-agent gathering task of agents with limited-range and bearing-only sensing that aim to preserve visibility-graph connectivity during the aggregation. The algorithm’s performance is evaluated against two benchmarks: an analytical solution proposed by Bellaiche and Bruckstein, which ensures gathering success, but progresses slowly, and VariAntNet , a neural network-based framework that gathers much faster, but shows moderate success rates in adverse initial agent configurations. Our method achieves high gathering success, with a speed nearly matching that of VariAntNet . In certain scenarios, it offers a viable alternative to existing approaches.
- Open Access
- 28 January 2026
- Published by Springer Nature in Artificial Life and Robotics
- Vol. 31 (1) , 302-316
Distributed and decentralized task allocation for heterogeneous swarms
This paper presents a multi-layered framework for fully distributed and decentralized task allocation in heterogeneous swarms, derived from interaction-based dynamics. This approach is built upon a baseline of homogeneous swarms composed of simple, autonomous, identical, locally sensing agents. Agents operate under the “flexible swarm” paradigm, which promotes global cohesion through local interactions that prevent swarm fragmentation. We demonstrate how a desired swarm behavior of exploration, task detection, and requirement fulfillment can emerge from local motion rules based solely on self-sensing without explicit inter-agent communication. Starting from a homogeneous baseline of identical agents, we extend the framework to heterogeneous swarms composed of agents with varying sensing capabilities and payloads. We introduce a novel interaction scheme in which two homogeneous groups, scouts and fire-extinguishers, are functionally coupled through local sensing, forming an emergent heterogeneous system. This coupled coordination enables distributed fire detection and suppression, enhancing robustness and scalability. The framework is validated through firefighting simulations, utilizing a heterogeneous swarm composed of scout agents with long-range sensing and fire-extinguishing agents with limited perception and actuation abilities. Through simple local motion rules, agents self-organize to detect and extinguish fires in a cooperative manner, driven solely by local sensing and interaction forces. Various fire suppression simulations demonstrate clear trade-offs between scouting and fire-extinguishing capacities. Our simulation results show that scouting dominates overall performance, whereas adding more fire-extinguishers provides only marginal improvement beyond a critical ratio. The results demonstrate that decentralized control of heterogeneous swarms enhances scalability, robustness, and efficiency even under direct communication denial. A simulation video demonstrating the proposed framework, illustrating the emergent coordination, task allocation dynamics, and analysis of a specific scenario, is available at https://youtu.be/dZqVxlhhzYc .
- 28 January 2026
- Published by Springer Nature in Artificial Life and Robotics
- Vol. 31 (1) , 302-316
Open AccessDistributed and decentralized task allocation for heterogeneous swarms
This paper presents a multi-layered framework for fully distributed and decentralized task allocation in heterogeneous swarms, derived from interaction-based dynamics. This approach is built upon a baseline of homogeneous swarms composed of simple, autonomous, identical, locally sensing agents. Agents operate under the “flexible swarm” paradigm, which promotes global cohesion through local interactions that prevent swarm fragmentation. We demonstrate how a desired swarm behavior of exploration, task detection, and requirement fulfillment can emerge from local motion rules based solely on self-sensing without explicit inter-agent communication. Starting from a homogeneous baseline of identical agents, we extend the framework to heterogeneous swarms composed of agents with varying sensing capabilities and payloads. We introduce a novel interaction scheme in which two homogeneous groups, scouts and fire-extinguishers, are functionally coupled through local sensing, forming an emergent heterogeneous system. This coupled coordination enables distributed fire detection and suppression, enhancing robustness and scalability. The framework is validated through firefighting simulations, utilizing a heterogeneous swarm composed of scout agents with long-range sensing and fire-extinguishing agents with limited perception and actuation abilities. Through simple local motion rules, agents self-organize to detect and extinguish fires in a cooperative manner, driven solely by local sensing and interaction forces. Various fire suppression simulations demonstrate clear trade-offs between scouting and fire-extinguishing capacities. Our simulation results show that scouting dominates overall performance, whereas adding more fire-extinguishers provides only marginal improvement beyond a critical ratio. The results demonstrate that decentralized control of heterogeneous swarms enhances scalability, robustness, and efficiency even under direct communication denial. A simulation video demonstrating the proposed framework, illustrating the emergent coordination, task allocation dynamics, and analysis of a specific scenario, is available at https://youtu.be/dZqVxlhhzYc .
- Open Access
Sensor to Pixels: Decentralized Swarm Gathering via Image-Based Reinforcement Learning
This study highlights the potential of image-based reinforcement learning methods for addressing swarm-related tasks. In multi-agent reinforcement learning, effective policy learning depends on how agents sense, interpret, and process inputs. Traditional approaches often rely on handcrafted feature extraction or raw vector-based representations, which limit the scalability and efficiency of learned policies concerning input order and size. In this work we propose an image-based reinforcement learning method for decentralized control of a multi-agent system, where observations are encoded as structured visual inputs that can be processed by Neural Networks, extracting its spatial features and producing novel decentralized motion control rules. We evaluate our approach on a multi-agent convergence task of agents with limited-range and bearing-only sensing that aim to keep the swarm cohesive during the aggregation. The algorithm's performance is evaluated against two benchmarks: an analytical solution proposed by Bellaiche and Bruckstein, which ensures convergence but progresses slowly, and VariAntNet, a neural network-based framework that converges much faster but shows medium success rates in hard constellations. Our method achieves high convergence, with a pace nearly matching that of VariAntNet. In some scenarios, it serves as the only practical alternative.
Open AccessSensor to Pixels: Decentralized Swarm Gathering via Image-Based Reinforcement Learning
This study highlights the potential of image-based reinforcement learning methods for addressing swarm-related tasks. In multi-agent reinforcement learning, effective policy learning depends on how agents sense, interpret, and process inputs. Traditional approaches often rely on handcrafted feature extraction or raw vector-based representations, which limit the scalability and efficiency of learned policies concerning input order and size. In this work we propose an image-based reinforcement learning method for decentralized control of a multi-agent system, where observations are encoded as structured visual inputs that can be processed by Neural Networks, extracting its spatial features and producing novel decentralized motion control rules. We evaluate our approach on a multi-agent convergence task of agents with limited-range and bearing-only sensing that aim to keep the swarm cohesive during the aggregation. The algorithm's performance is evaluated against two benchmarks: an analytical solution proposed by Bellaiche and Bruckstein, which ensures convergence but progresses slowly, and VariAntNet, a neural network-based framework that converges much faster but shows medium success rates in hard constellations. Our method achieves high convergence, with a pace nearly matching that of VariAntNet. In some scenarios, it serves as the only practical alternative.
- 6 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Robotics
- Vol. 41 (15523098) , 4100-4119
Time, Travel, and Energy in the Uniform Dispersion Problem
We investigate the algorithmic problem of uniformly dispersing a swarm of robots in an unknown, gridlike environment. In this setting, our goal is to study the relationships between performance metrics and robot capabilities. We introduce a formal model comparing dispersion algorithms based on makespan, traveled distance, energy consumption, sensing, communication, and memory. Using this framework, we classify uniform dispersion algorithms according to their capability requirements and performance. We prove that while makespan and travel can be minimized in all environments, energy cannot, if the swarm's sensing range is bounded. In contrast, we show that energy can be minimized by “ant-like” robots in synchronous settings and asymptotically minimized in asynchronous settings, provided the environment is topologically simply connected, by using our “Find-Corner Depth-First Search” (FCDFS) algorithm. Our theoretical and experimental results show that FCDFS significantly outperforms known algorithms. Our findings reveal key limitations in designing swarm robotics systems for unknown environments, emphasizing the role of topology in energy-efficient dispersion.
- 6 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Robotics
- Vol. 41 (15523098) , 4100-4119
Time, Travel, and Energy in the Uniform Dispersion Problem
We investigate the algorithmic problem of uniformly dispersing a swarm of robots in an unknown, gridlike environment. In this setting, our goal is to study the relationships between performance metrics and robot capabilities. We introduce a formal model comparing dispersion algorithms based on makespan, traveled distance, energy consumption, sensing, communication, and memory. Using this framework, we classify uniform dispersion algorithms according to their capability requirements and performance. We prove that while makespan and travel can be minimized in all environments, energy cannot, if the swarm's sensing range is bounded. In contrast, we show that energy can be minimized by “ant-like” robots in synchronous settings and asymptotically minimized in asynchronous settings, provided the environment is topologically simply connected, by using our “Find-Corner Depth-First Search” (FCDFS) algorithm. Our theoretical and experimental results show that FCDFS significantly outperforms known algorithms. Our findings reveal key limitations in designing swarm robotics systems for unknown environments, emphasizing the role of topology in energy-efficient dispersion.
- Open Access
- 3 January 2025
- Published by Agora University of Oradea in International Journal of Computers Communications & Control
- Vol. 20 (1)
AntPaP: Patrolling and Fair Partitioning of Graphs by A(ge)nts Leaving Pheromone Traces
A team of identical and oblivious ant-like agents – a(ge)nts – leaving pheromone traces, are programmed to jointly patrol an area modeled as a graph. They perform this task using simple local interactions, while also achieving the important byproduct of partitioning the graph into roughly equal-sized disjoint sub-graphs. Each a(ge)nt begins to operate at an arbitrary initial location, and throughout its work does not acquire any information on either the shape or size of the graph, or the number or whereabouts of other a(ge)nts. Graph partitioning occurs spontaneously, as each of the a(ge)nts patrols and expands its own pheromone-marked sub-graph, or region. This graph partitioning algorithm is inspired by molecules hitting the borders of air filled elastic balloons: an a(ge)nt that hits a border edge from the interior of its region more frequently than an external a(ge)nt hits the same edge from an adjacent vertex in the neighboring region, may conquer that adjacent vertex, expanding its region at the expense of the neighbor. Since the rule of patrolling a region ensures that each vertex is visited with a frequency inversely proportional to the size of the region, in terms of vertex count, a smaller region will effectively exert higher “pressure” at its borders, and conquer adjacent vertices from a larger region, thereby increasing the smaller region and shrinking the larger. The algorithm, therefore, tends to equalize the sizes of the regions patrolled, resembling a set of perfectly elastic physical balloons, confined to a closed volume and filled with an equal amount of air. The pheromone based local interactions of agents eventually cause the system to evolve into a partition that is close to balanced rather quickly, and if the graph and the number of a(ge)nts remain unchanged, it is guaranteed that the system settles into a stable and balanced partition.
- 3 January 2025
- Published by Agora University of Oradea in International Journal of Computers Communications & Control
- Vol. 20 (1)
Open AccessAntPaP: Patrolling and Fair Partitioning of Graphs by A(ge)nts Leaving Pheromone Traces
A team of identical and oblivious ant-like agents – a(ge)nts – leaving pheromone traces, are programmed to jointly patrol an area modeled as a graph. They perform this task using simple local interactions, while also achieving the important byproduct of partitioning the graph into roughly equal-sized disjoint sub-graphs. Each a(ge)nt begins to operate at an arbitrary initial location, and throughout its work does not acquire any information on either the shape or size of the graph, or the number or whereabouts of other a(ge)nts. Graph partitioning occurs spontaneously, as each of the a(ge)nts patrols and expands its own pheromone-marked sub-graph, or region. This graph partitioning algorithm is inspired by molecules hitting the borders of air filled elastic balloons: an a(ge)nt that hits a border edge from the interior of its region more frequently than an external a(ge)nt hits the same edge from an adjacent vertex in the neighboring region, may conquer that adjacent vertex, expanding its region at the expense of the neighbor. Since the rule of patrolling a region ensures that each vertex is visited with a frequency inversely proportional to the size of the region, in terms of vertex count, a smaller region will effectively exert higher “pressure” at its borders, and conquer adjacent vertices from a larger region, thereby increasing the smaller region and shrinking the larger. The algorithm, therefore, tends to equalize the sizes of the regions patrolled, resembling a set of perfectly elastic physical balloons, confined to a closed volume and filled with an equal amount of air. The pheromone based local interactions of agents eventually cause the system to evolve into a partition that is close to balanced rather quickly, and if the graph and the number of a(ge)nts remain unchanged, it is guaranteed that the system settles into a stable and balanced partition.
- 5 January 2024
- Published by Elsevier in Robotics and Autonomous Systems
- Vol. 173
Defense against smart invaders with swarms of sweeping agents
- 5 January 2024
- Published by Elsevier in Robotics and Autonomous Systems
- Vol. 173
Defense against smart invaders with swarms of sweeping agents
- Open Access
Defense Against Smart Invaders with Swarms of Sweeping Agents
The goal of this research is to devise guaranteed defense policies that allow to protect a given region from the entrance of smart mobile invaders by detecting them using a team of defending agents equipped with identical line sensors. By designing cooperative defense strategies that ensure all invaders are detected, conditions on the defenders' speed are derived. Successful accomplishment of the defense task implies invaders with a known limit on their speed cannot slip past the defenders and enter the guarded region undetected. The desired outcome of the defense protocols is to defend the area and additionally to expand it as much as possible. Expansion becomes possible if the defenders' speed exceeds a critical speed that is necessary to only defend the initial region. We present results on the total search time, critical speeds and maximal expansion possible for two types of novel pincer-movement defense processes, circular and spiral, for any even number of defenders. The proposed spiral process allows to detect invaders at nearly the lowest theoretically optimal speed, and if this speed is exceeded, it also allows to expand the protected region almost to the maximal area.
Open AccessDefense Against Smart Invaders with Swarms of Sweeping Agents
The goal of this research is to devise guaranteed defense policies that allow to protect a given region from the entrance of smart mobile invaders by detecting them using a team of defending agents equipped with identical line sensors. By designing cooperative defense strategies that ensure all invaders are detected, conditions on the defenders' speed are derived. Successful accomplishment of the defense task implies invaders with a known limit on their speed cannot slip past the defenders and enter the guarded region undetected. The desired outcome of the defense protocols is to defend the area and additionally to expand it as much as possible. Expansion becomes possible if the defenders' speed exceeds a critical speed that is necessary to only defend the initial region. We present results on the total search time, critical speeds and maximal expansion possible for two types of novel pincer-movement defense processes, circular and spiral, for any even number of defenders. The proposed spiral process allows to detect invaders at nearly the lowest theoretically optimal speed, and if this speed is exceeded, it also allows to expand the protected region almost to the maximal area.
- 8 September 2023
- Published by Springer Nature
- p. 89-100
Spiral Sweeping Protocols for Detection of Smart Evaders
- 8 September 2023
- Published by Springer Nature
- p. 89-100
Spiral Sweeping Protocols for Detection of Smart Evaders
- 25 February 2023
- Published by Springer Nature
- p. 175-207
Modular ADMM-Based Strategies for Optimized Compression, Restoration, and Distributed Representations of Visual Data
- 25 February 2023
- Published by Springer Nature
- p. 175-207
Modular ADMM-Based Strategies for Optimized Compression, Restoration, and Distributed Representations of Visual Data