Synergizing sub-symbolic and symbolic AI
The scientists have further optimized the "RH5" system in the VeryHuman project.
© DFKI, Annemarie Popp
DFKI unveils pioneering approach to safe and verifiable humanoid walking.
Recent advances in robotics based on data-driven AI hold promise for a wide range of practical applications. However, ensuring the safety of these applications is a challenge. The German Research Center for Artificial Intelligence (DFKI) in Bremen has developed innovative control methods for complex systems, combining the advantages of fast self-learning and reliable verification via symbolic models. With this hybrid AI approach, the project funded by the Federal Ministry of Education and Research (BMBF) offers a ground-breaking solution to the challenges of humanoid robotics.
As sub-symbolic AI, like deep learning, continues to advance, its limitations in safety and reliability are becoming more apparent. Verification and stability are crucial in safety-critical domains such as humanoid robotics, which is rapidly evolving into a versatile tool for various applications. However, proving the correctness of AI-based self-learning algorithms is challenging due to their uncertain inferences and opaque decision-making processes.
Innovative hybrid AI approach to learn and verify complex robotic behavior
In the VeryHuman project, DFKI researchers addressed these challenges by integrating symbolic and sub-symbolic AI approaches. Specifically, they used symbolic specifications in reinforcement learning, where a system is rewarded for producing results that are mathematically verifiable.
Combining sub-symbolic, self-learning algorithms with those based on mathematical rules and abstractions in a single system has proven difficult. Machine learning decisions are not based on symbolic calculations and cannot be explained by logical rules. Therefore, DFKI combined the expertise of its two Bremen-based research departments: Robotics Innovation Center, led by Prof. Dr. Frank Kirchner, and Cyber-Physical Systems, led by Prof. Dr. Rolf Drechsler. The goal was to develop an AI-based control system capable of achieving human-like capabilities, particularly in demonstrating safe and stable dynamic walking and other complex movements in humanoid robots.
Deriving rewards for reinforcement learning from symbolic descriptions
By using symbolic specifications in reinforcement learning, such as simple language to describe the robot’s behavior, the project team created abstract kinematic models from the system that can be symbolically validated. These abstractions allow the definition of reward functions for reinforcement learning and the robot to mathematically verify its decisions based on the models. Thus, the reliability of the system’s decisions is improved, ensuring stable and predictable movements, and reducing the risk of misbehavior or unexpected actions.
Additionally, the intended behavior of the robot was modeled as a hybrid automaton, a mathematical model that describes both continuous and discrete behavior. This reduces the system’s state space, allowing for more efficient reinforcement learning.
Fast dynamic walking with DFKI’s RH5 humanoid robot
Furthermore, the project successfully achieved dynamic walking on DFKI’s RH5 humanoid robot by combining the zero-moment point method (the point on a robot’s support area where the resulting ground force does not create a tipping moment) with the whole-body control approach in a tailored manner suitable for achieving high performance in position-controlled robots. This enabled stable and robust dynamic walking at varying speeds and step lengths, effectively pushing the limits of the system in terms of both speed and range of motion.
To the researchers’ knowledge, this is the first time a humanoid robot has dynamically walked up to 0.43 m/s. Excluding systems with active toe joints, RH5 is among the fastest humanoids of similar size and actuation modalities. To continuously improve RH5’s behavior, the researchers also used simulation and optimal control algorithms based on the symbolic model.
Improved efficiency and safety for AI applications in high-risk areas
Since precise modeling and optimization of motion sequences enhance both the safety and efficiency of robots, the hybrid AI approach developed in VeryHuman can serve as a blueprint for generating reward functions from symbolic AI and reasoning. This is particularly relevant for real-world applications where the safety of robots and their environment is paramount.
VeryHuman was funded by the German Federal Ministry of Education and Research (BMBF) from June 2020 to May 2024 under grant number 01IW20004.
Wissenschaftliche Ansprechpartner:
Dr. Melya Boukheddimi
Robotics Innovation Center
Phone: +49 421 17845 4192
Mail: melya.boukheddimi@dfki.de
Assist. Prof. Dr. Shivesh Kumar
Robotics Innovation Center
Phone: +49 421 17845 4144
Mail: shivesh.kumar@dfki.de
Prof. Dr. Christoph Lüth
Cyber-Physical Systems
Phone: +49 421 218 59830
Mail: Christoph.Lüth@dfki.de
Weitere Informationen:
https://cloud.dfki.de/owncloud/index.php/s/kAEknoSKMBbsZZb Here, you can find pictures of RH5, the robotic system used in the project. You may use the images naming the source “DFKI, Annemarie Popp”.
https://www.dfki.de/en/web/news/synergizing-sub-symbolic-and-symbolic-ai
Media Contact
All latest news from the category: Information Technology
Here you can find a summary of innovations in the fields of information and data processing and up-to-date developments on IT equipment and hardware.
This area covers topics such as IT services, IT architectures, IT management and telecommunications.
Newest articles
Innovative 3D printed scaffolds offer new hope for bone healing
Researchers at the Institute for Bioengineering of Catalonia have developed novel 3D printed PLA-CaP scaffolds that promote blood vessel formation, ensuring better healing and regeneration of bone tissue. Bone is…
The surprising role of gut infection in Alzheimer’s disease
ASU- and Banner Alzheimer’s Institute-led study implicates link between a common virus and the disease, which travels from the gut to the brain and may be a target for antiviral…
Molecular gardening: New enzymes discovered for protein modification pruning
How deubiquitinases USP53 and USP54 cleave long polyubiquitin chains and how the former is linked to liver disease in children. Deubiquitinases (DUBs) are enzymes used by cells to trim protein…
The full realization of the potential of artificial intelligence will be the main force for the development and simplification of technological processes. Already, leading innovations in artificial intelligence, AR, IoT, quantum computing, GreenTech and Deep Tech are simplifying the system for developing digital business models and helping to optimize workflows. This is the near future of most industries, including logistics. Currently, the latest ideas of artificial intelligence allow for accurate calculations of delivery costs, create a wide range of different capabilities that simplify work planning, allow for security control and take into account possible risks. This allows for the autonomous performance of many functions, which allows entrepreneurs and customers to save a significant amount of their own time in the process of sending various types of goods: GLS Zuschläge
https://dashboard.shipstage.com/faq/article/71-wann-fallen-bei-gls-zuschlage/ Together, such technical innovations and digital business models provide an excellent foundation for development in the 21st century.