About this Research Topic
Humanoid robots attract growing research interests from different communities, both as tools for artificial intelligence research and neurocognitive interaction assessment and, as enabling technology with high societal impacts as personal robots for health, education, and entertainment. These robots, modeled on the basis of the embodiment of neural systems in software and hardware devices, are characterized by a high number of degrees of freedom, complex end effectors and locomotion mechanisms on the hardware side. On the control side, they are characterized by the intrinsic and complex variety of their behavioral skills that are learned (imitation, reinforcement, statistical), for instance, learning-by-demonstration, data-driven approaches to humanoid arm programming, and the most recent AI-based approaches to manipulation and locomotion control.
Targeting co-existence or physical interactions with humans, both intelligence and safety are of great importance for service-oriented humanoid robots. Intelligence and safety correspond to software and hardware levels of humanoid robots, respectively. There has been recent progress in both areas, such as the quick emergence of learning-based artificial intelligence and soft robotics, bringing paradigm changes to the brain-inspired humanoid design, control, and applications.
This Research Topic focuses on the intelligence and safety of humanoid robots, and the interest extends to the interactions between the two areas:
1) intelligence resulting from safety: mechanically programmable intelligence for soft humanoid robots that does not put heavy reliance on control;
2) safety resulting from intelligence: cybersecurity challenges and solutions arising from intelligent humanoids with learning and adaptation capabilities.
We welcome manuscript submissions addressing the design, control, and application of safe and intelligent humanoid parts and systems.
Topics include but are not limited to the following:
- Design of soft and compliant humanoid robots, for instance, robotic fingers, hands, arms, legs.
- Decentralized control or high-level control of humanoid robotic fingers, hands, arms, legs with neural networks.
- Intelligent interaction between human and humanoid robots for human-robot cooperative tasks, for instance, lifting the table.
- Techniques to guarantee safety between human and humanoid robots, corresponding to the software and hardware levels.
Keywords: learning-based artificial intelligence, soft robotics, brain-inspired humanoid robots, Intelligence, Safety, Design, Control
Important Note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.