Soft robotic technologies have introduced new paradigms in the design and development of robots. This shift in outlook presents new challenges and opportunities for modelling, control, and design of these robots. Traditional techniques based on analytical models have proven to be insufficient to tackle these new challenges. This is because of their highly nonlinear, time-varying and high-dimensional characteristics coupled with immense diversity in their design. Machine learning-based approaches provide a promising alternative to traditional analytical approaches. Learning-based approaches have proven to be a valuable tool for control, data-processing, and design optimization of nonlinear systems in alternate fields. However, their usage has been largely limited and unexplored, in spite of their potential value.
This Research Topic aims to investigate and advance new learning-based approaches for modelling, control, and design of soft robots. Specifically, we aim to introduce novel exciting concepts from the machine learning community to the soft robotics community to tackle the numerous challenges in soft robotics. This includes the modelling and control of soft-bodied systems, data processing of soft tactile sensors and the design optimization of soft-bodied systems. Articles that identify novel usage of machine learning tools in the research and application of soft robots, improved learning techniques catered for soft robots and reviews/perspectives/commentaries on challenges and opportunities for machine learning researchers in the field of soft robotics are desired. The Research Topic also promotes articles on hybrid model-free and model-based approaches, as well as comparative studies.
Relevant submissions for this Research Topic include, but are not limited to, the following:
• Learning-based kinematic and dynamic control of soft robots
• Hybrid learning approaches
• Learning-based soft sensor modelling
• Closing the sensory motor loop using reinforcement learning
• Benchmarking experiments/simulations for comparing modelling and
control strategies
• End-to-end control/model architectures
• Learning-based design of soft robots
• Bio-inspired learning architectures
• Perspectives on challenges and open questions
• Transfer learning among soft robots
• Damage detection and intelligent adaptation
• Machine learning for soft tactile sensing
• Deep learning in soft robotics
Soft robotic technologies have introduced new paradigms in the design and development of robots. This shift in outlook presents new challenges and opportunities for modelling, control, and design of these robots. Traditional techniques based on analytical models have proven to be insufficient to tackle these new challenges. This is because of their highly nonlinear, time-varying and high-dimensional characteristics coupled with immense diversity in their design. Machine learning-based approaches provide a promising alternative to traditional analytical approaches. Learning-based approaches have proven to be a valuable tool for control, data-processing, and design optimization of nonlinear systems in alternate fields. However, their usage has been largely limited and unexplored, in spite of their potential value.
This Research Topic aims to investigate and advance new learning-based approaches for modelling, control, and design of soft robots. Specifically, we aim to introduce novel exciting concepts from the machine learning community to the soft robotics community to tackle the numerous challenges in soft robotics. This includes the modelling and control of soft-bodied systems, data processing of soft tactile sensors and the design optimization of soft-bodied systems. Articles that identify novel usage of machine learning tools in the research and application of soft robots, improved learning techniques catered for soft robots and reviews/perspectives/commentaries on challenges and opportunities for machine learning researchers in the field of soft robotics are desired. The Research Topic also promotes articles on hybrid model-free and model-based approaches, as well as comparative studies.
Relevant submissions for this Research Topic include, but are not limited to, the following:
• Learning-based kinematic and dynamic control of soft robots
• Hybrid learning approaches
• Learning-based soft sensor modelling
• Closing the sensory motor loop using reinforcement learning
• Benchmarking experiments/simulations for comparing modelling and
control strategies
• End-to-end control/model architectures
• Learning-based design of soft robots
• Bio-inspired learning architectures
• Perspectives on challenges and open questions
• Transfer learning among soft robots
• Damage detection and intelligent adaptation
• Machine learning for soft tactile sensing
• Deep learning in soft robotics