Michael Beetz
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Michael Beetz has a total of 386 co-authors. Here are the top co-authors by number of shared publications:
Moritz Tenorth
31 shared publicationsRadu Bogdan Rusu
Willow Garage, Inc., Menlo Park, CA, USA
23 shared publicationsNico Blodow
Intelligent Autonomous Systems Group, Technische Universität München, Germany
19 shared publications- Alexis Maldonado
Technische Universität
17 shared publications Dejan Pangercic
Intelligent Autonomous Systems Group, TU Munich, Germany
16 shared publicationsBernd Radig
Technische Universität München, Germany
12 shared publications
Latest Publications
- Open Access
- 27 August 2026
- Published by Springer Nature in Artificial Intelligence Review
- Vol. 59 (10) , 213
How metacognitive architectures remember their own thoughts: a systematic scoping review
Metacognition has gained significant attention for its potential to enhance autonomy and adaptability of artificial agents but remains a fragmented field: diverse theories, terminologies, and design choices have led to disjointed developments and limited comparability across systems. Existing overviews remain at a conceptual level that is undiscerning to the underlying algorithms, representations, and their respective effectiveness. We address this gap by performing a systematic scoping review. Reports were included if they described techniques enabling Computational Metacognitive Architectures (CMAs) to model, store, remember, and process their episodic metacognitive experiences , one of Flavell’s (1979) three foundational components of metacognition. Searches were conducted in 16 databases between December 2023 and June 2024. Data were charted using a 20-item framework considering pertinent aspects and analysed via structured narrative synthesis. A total of 101 reports on 35 distinct CMAs were included. Our findings show that metacognitive experiences may boost system performance and explainability, e.g., via self-repair. However, lack of standardisation and limited evaluations may hinder progress: only 17% of CMAs were quantitatively evaluated regarding this review’s focus, and significant terminological inconsistency limits cross-architecture synthesis. Systems also varied widely in memory content, data types, and employed algorithms. Limitations include the non-iterative nature of the search query, heterogeneous data availability, and an under-representation of sub-symbolic CMAs. Future research should focus on standardisation and evaluation, e.g., via community-driven challenges, and on transferring promising principles to emergent systems.
- 27 August 2026
- Published by Springer Nature in Artificial Intelligence Review
- Vol. 59 (10) , 213
Open AccessHow metacognitive architectures remember their own thoughts: a systematic scoping review
Metacognition has gained significant attention for its potential to enhance autonomy and adaptability of artificial agents but remains a fragmented field: diverse theories, terminologies, and design choices have led to disjointed developments and limited comparability across systems. Existing overviews remain at a conceptual level that is undiscerning to the underlying algorithms, representations, and their respective effectiveness. We address this gap by performing a systematic scoping review. Reports were included if they described techniques enabling Computational Metacognitive Architectures (CMAs) to model, store, remember, and process their episodic metacognitive experiences , one of Flavell’s (1979) three foundational components of metacognition. Searches were conducted in 16 databases between December 2023 and June 2024. Data were charted using a 20-item framework considering pertinent aspects and analysed via structured narrative synthesis. A total of 101 reports on 35 distinct CMAs were included. Our findings show that metacognitive experiences may boost system performance and explainability, e.g., via self-repair. However, lack of standardisation and limited evaluations may hinder progress: only 17% of CMAs were quantitatively evaluated regarding this review’s focus, and significant terminological inconsistency limits cross-architecture synthesis. Systems also varied widely in memory content, data types, and employed algorithms. Limitations include the non-iterative nature of the search query, heterogeneous data availability, and an under-representation of sub-symbolic CMAs. Future research should focus on standardisation and evaluation, e.g., via community-driven challenges, and on transferring promising principles to emergent systems.
- Open Access
- 1 August 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Biomedical Engineering
- Vol. 73 (8) , 2723-2735
CogniFuse and Multimodal Deformers: An Extended Study on Benchmarking and Modeling Biosignal Fusion
Human physiological signals reflect complex biological processes and provide important insights into physical and mental states. Extracting such information from biosignal data collected during everyday activities holds great potential for real-time monitoring of physical and mental states, but is challenging due to noise and artifacts. To address this, we introduce CogniFuse, the first publicly available multi-task benchmark for multimodal biosignal fusion in such unconstrained environments. In addition, we develop a comprehensive benchmarking pipeline that emphasizes comparability, reproducibility, accessibility, and usability, while demonstrating robustness across architectures, tasks, and model sizes. For many biosignals, particularly electrophysiological signals, information in different frequency bands is critical for assessing physiological states. Motivated by this, we propose a family of Multimodal Deformer models that capture multi-level power features along with both long- and short-term temporal dependencies across multiple biosignal modalities. In particular, our Multi-Channel Deformer achieves the highest average benchmark score, outperforming all models of comparison. By advancing multimodal biosignal fusion in everyday settings, this work supports real-time monitoring of physical and mental states outside highly controlled clinical conditions. To ensure full transparency and reproducibility, and to facilitate future research, all code and data are made publicly available.
- 1 August 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Biomedical Engineering
- Vol. 73 (8) , 2723-2735
Open AccessCogniFuse and Multimodal Deformers: An Extended Study on Benchmarking and Modeling Biosignal Fusion
Human physiological signals reflect complex biological processes and provide important insights into physical and mental states. Extracting such information from biosignal data collected during everyday activities holds great potential for real-time monitoring of physical and mental states, but is challenging due to noise and artifacts. To address this, we introduce CogniFuse, the first publicly available multi-task benchmark for multimodal biosignal fusion in such unconstrained environments. In addition, we develop a comprehensive benchmarking pipeline that emphasizes comparability, reproducibility, accessibility, and usability, while demonstrating robustness across architectures, tasks, and model sizes. For many biosignals, particularly electrophysiological signals, information in different frequency bands is critical for assessing physiological states. Motivated by this, we propose a family of Multimodal Deformer models that capture multi-level power features along with both long- and short-term temporal dependencies across multiple biosignal modalities. In particular, our Multi-Channel Deformer achieves the highest average benchmark score, outperforming all models of comparison. By advancing multimodal biosignal fusion in everyday settings, this work supports real-time monitoring of physical and mental states outside highly controlled clinical conditions. To ensure full transparency and reproducibility, and to facilitate future research, all code and data are made publicly available.
- Open Access
- 20 July 2026
- Published by Springer Nature in KI - Künstliche Intelligenz
- p. 1-6
From Frames to Pouring: The CRAM Cognitive Architecture for Everyday Robot Manipulation
The Cognitive Robot Abstract Machine (CRAM) was developed to enable robots to perform everyday manipulation tasks in human environments by transforming underspecified task instructions into context-sensitive, executable actions. Rather than proposing a single planning algorithm, CRAM represents a cognitive architecture grounded in symbolic knowledge representation, generalized action plans, and introspective execution. This paper traces the evolution of the artificial intelligence ideas that shaped CRAM, from early work on frames, scripts, program interpretation and action-centered planning to contemporary developments in cognitive robotics. We show how these ideas are operationalized in the CRAM architecture and how successive extensions, including semantic digital twins, episodic memories, and dual-process reasoning, support robust execution, explanation and adaptation. In addition, we discuss the Virtual Research Building as an experimental substrate that enables systematic and reproducible evaluation of CRAM components. Finally, we outline future challenges for CRAM, highlighting the need to complement its top-down task-driven paradigm with more interaction-centered and enactive approaches for long-term deployment in human environments.
- 20 July 2026
- Published by Springer Nature in KI - Künstliche Intelligenz
- p. 1-6
Open AccessFrom Frames to Pouring: The CRAM Cognitive Architecture for Everyday Robot Manipulation
The Cognitive Robot Abstract Machine (CRAM) was developed to enable robots to perform everyday manipulation tasks in human environments by transforming underspecified task instructions into context-sensitive, executable actions. Rather than proposing a single planning algorithm, CRAM represents a cognitive architecture grounded in symbolic knowledge representation, generalized action plans, and introspective execution. This paper traces the evolution of the artificial intelligence ideas that shaped CRAM, from early work on frames, scripts, program interpretation and action-centered planning to contemporary developments in cognitive robotics. We show how these ideas are operationalized in the CRAM architecture and how successive extensions, including semantic digital twins, episodic memories, and dual-process reasoning, support robust execution, explanation and adaptation. In addition, we discuss the Virtual Research Building as an experimental substrate that enables systematic and reproducible evaluation of CRAM components. Finally, we outline future challenges for CRAM, highlighting the need to complement its top-down task-driven paradigm with more interaction-centered and enactive approaches for long-term deployment in human environments.
- Open Access
Implementing Knowledge Representation and Reasoning with Object Oriented Design
This paper introduces KRROOD, a framework designed to bridge the integration gap between modern software engineering and Knowledge Representation & Reasoning (KR&R) systems. While Object-Oriented Programming (OOP) is the standard for developing complex applications, existing KR&R frameworks often rely on external ontologies and specialized languages that are difficult to integrate with imperative code. KRROOD addresses this by treating knowledge as a first-class programming abstraction using native class structures, bridging the gap between the logic programming and OOP paradigms. We evaluate the system on the OWL2Bench benchmark and a human-robot task learning scenario. Experimental results show that KRROOD achieves strong performance while supporting the expressive reasoning required for real-world autonomous systems.
Open AccessImplementing Knowledge Representation and Reasoning with Object Oriented Design
This paper introduces KRROOD, a framework designed to bridge the integration gap between modern software engineering and Knowledge Representation & Reasoning (KR&R) systems. While Object-Oriented Programming (OOP) is the standard for developing complex applications, existing KR&R frameworks often rely on external ontologies and specialized languages that are difficult to integrate with imperative code. KRROOD addresses this by treating knowledge as a first-class programming abstraction using native class structures, bridging the gap between the logic programming and OOP paradigms. We evaluate the system on the OWL2Bench benchmark and a human-robot task learning scenario. Experimental results show that KRROOD achieves strong performance while supporting the expressive reasoning required for real-world autonomous systems.
- Open Access
- 17 December 2025
- Published by Springer Nature in International Journal of Social Robotics
- Vol. 17 (12) , 2855-2857
Editorial: Knowledge, Learning, Planning and Human Behavior Modeling for Autonomous Social Robots
- 17 December 2025
- Published by Springer Nature in International Journal of Social Robotics
- Vol. 17 (12) , 2855-2857
Open AccessEditorial: Knowledge, Learning, Planning and Human Behavior Modeling for Autonomous Social Robots
- 14 June 2025
- Published by Springer Nature
- p. 209-253
Knowledge Representation and Reasoning
- 8 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 01-09
Interactive E-Learning Environment for Cognitive Robotics
While robots are increasingly present in everyday environments as vacuum cleaners, lawnmowers, or voice assistants, cognitive robots that autonomously help the elderly, prepare meals, do the laundry, or clean up are still missing. This is due to various reasons. Besides such robots being less cost-efficient, needing more knowledge, and the ability to safely perform task variations in changing environments, successful research applications are rarely adopted by industry. Although there are robots that already are able to prepare meals, clean the table, or fold the laundry, these applications cannot easily be implemented by someone who is not familiar with the available robots, their cognitive architecture, and their knowledge framework. In order to help more people get familiar with robotics, reuse existing infrastructure in simulation environments, and implement their own applications on this basis, we propose an immersive E-Learning environment for Cognitive Robotics that not only introduces and describes the different aspects needed for developing robotic applications, but also offers easy-to-use tutorials on how to program robots that are based on simulation environments that link to the different software modules a robot needs to execute actions. We define a set of competences for Cognitive Robotics that covers the required content-related and process-related competences. We present the underlying didactical approaches such as APKIPE (Ger. AVIVA), adaptive learning, and self-directed learning, as well as an approach how to evaluate the effectiveness of the proposed platform. Lastly, we demonstrate how the learning environment based on the premises of the described didactical approaches can be used to achieve the competences required to develop control systems for Cognitive Robotics.
- 8 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 01-09
Interactive E-Learning Environment for Cognitive Robotics
While robots are increasingly present in everyday environments as vacuum cleaners, lawnmowers, or voice assistants, cognitive robots that autonomously help the elderly, prepare meals, do the laundry, or clean up are still missing. This is due to various reasons. Besides such robots being less cost-efficient, needing more knowledge, and the ability to safely perform task variations in changing environments, successful research applications are rarely adopted by industry. Although there are robots that already are able to prepare meals, clean the table, or fold the laundry, these applications cannot easily be implemented by someone who is not familiar with the available robots, their cognitive architecture, and their knowledge framework. In order to help more people get familiar with robotics, reuse existing infrastructure in simulation environments, and implement their own applications on this basis, we propose an immersive E-Learning environment for Cognitive Robotics that not only introduces and describes the different aspects needed for developing robotic applications, but also offers easy-to-use tutorials on how to program robots that are based on simulation environments that link to the different software modules a robot needs to execute actions. We define a set of competences for Cognitive Robotics that covers the required content-related and process-related competences. We present the underlying didactical approaches such as APKIPE (Ger. AVIVA), adaptive learning, and self-directed learning, as well as an approach how to evaluate the effectiveness of the proposed platform. Lastly, we demonstrate how the learning environment based on the premises of the described didactical approaches can be used to achieve the competences required to develop control systems for Cognitive Robotics.
- 8 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Cloud-Based Digital Twin for Cognitive Robotics
The paper presents a novel cloud-based digital twin learning platform for teaching and training concepts of cognitive robotics. Instead of forcing interested learners or students to install a new operating system and bulky, fragile software onto their personal laptops just to solve tutorials or coding assignments of a single lecture on robotics, it would be beneficial to avoid technical setups and directly dive into the content of cognitive robotics. To achieve this, the authors utilize containerization technologies and Kubernetes to deploy and operate containerized applications, including robotics simulation environments and software collections based on the Robot operating System (ROS). The web-based Integrated Development Environment JupyterLab is integrated with RvizWeb and XPRA to provide real-time visualization of sensor data and robot behavior in a user-friendly environment for interacting with robotics software. The paper also discusses the application of the platform in teaching Knowledge Representation, Reasoning, Acquisition and Retrieval, and Task-Executives. The authors conclude that the proposed platform is a valuable tool for education and research in cognitive robotics, and that it has the potential to democratize access to these fields. The platform has already been successfully employed in various academic courses, demonstrating its effectiveness in fostering knowledge and skill development.
- 8 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Cloud-Based Digital Twin for Cognitive Robotics
The paper presents a novel cloud-based digital twin learning platform for teaching and training concepts of cognitive robotics. Instead of forcing interested learners or students to install a new operating system and bulky, fragile software onto their personal laptops just to solve tutorials or coding assignments of a single lecture on robotics, it would be beneficial to avoid technical setups and directly dive into the content of cognitive robotics. To achieve this, the authors utilize containerization technologies and Kubernetes to deploy and operate containerized applications, including robotics simulation environments and software collections based on the Robot operating System (ROS). The web-based Integrated Development Environment JupyterLab is integrated with RvizWeb and XPRA to provide real-time visualization of sensor data and robot behavior in a user-friendly environment for interacting with robotics software. The paper also discusses the application of the platform in teaching Knowledge Representation, Reasoning, Acquisition and Retrieval, and Task-Executives. The authors conclude that the proposed platform is a valuable tool for education and research in cognitive robotics, and that it has the potential to democratize access to these fields. The platform has already been successfully employed in various academic courses, demonstrating its effectiveness in fostering knowledge and skill development.
- 5 December 2023
- Published by Springer Nature
- p. 199-210
Ein interaktives strategisches Missionsmanagementsystem für intuitive Mensch-Roboter-Kooperation
- 5 December 2023
- Published by Springer Nature
- p. 199-210
Ein interaktives strategisches Missionsmanagementsystem für intuitive Mensch-Roboter-Kooperation
- Open Access
Integrating Transformations in Probabilistic Circuits
This study addresses the predictive limitation of probabilistic circuits and introduces transformations as a remedy to overcome it. We demonstrate this limitation in robotic scenarios. We motivate that independent component analysis is a sound tool to preserve the independence properties of probabilistic circuits. Our approach is an extension of joint probability trees, which are model-free deterministic circuits. By doing so, it is demonstrated that the proposed approach is able to achieve higher likelihoods while using fewer parameters compared to the joint probability trees on seven benchmark data sets as well as on real robot data. Furthermore, we discuss how to integrate transformations into tree-based learning routines. Finally, we argue that exact inference with transformed quantile parameterized distributions is not tractable. However, our approach allows for efficient sampling and approximate inference.
Open AccessIntegrating Transformations in Probabilistic Circuits
This study addresses the predictive limitation of probabilistic circuits and introduces transformations as a remedy to overcome it. We demonstrate this limitation in robotic scenarios. We motivate that independent component analysis is a sound tool to preserve the independence properties of probabilistic circuits. Our approach is an extension of joint probability trees, which are model-free deterministic circuits. By doing so, it is demonstrated that the proposed approach is able to achieve higher likelihoods while using fewer parameters compared to the joint probability trees on seven benchmark data sets as well as on real robot data. Furthermore, we discuss how to integrate transformations into tree-based learning routines. Finally, we argue that exact inference with transformed quantile parameterized distributions is not tractable. However, our approach allows for efficient sampling and approximate inference.