Computational Design & Fabrication of Robots
Event details
| Date | 11.02.2020 |
| Hour | 12:45 › 13:45 |
| Speaker | Dr. Josie Hughes, Distributed Robotics Lab, MIT |
| Location | |
| Category | Conferences - Seminars |
Abstract:
Automating the design and creation of complex robots is challenging due to the complexity of the design search space and physical processes required. To address this, data-driven approaches are required to understand how to design and optimize robotic structures for a given task. This talk introduces a number of techniques and processes for the computational design of robots, focusing on automated design, rapid fabrication, and task-specific learning. This includes approaches ranging from biologically inspired design, to developing terrain optimized robots by searching over 10,000s of possible designs, and Bayesian based approaches for rapid task learning. Different application scenarios for these approaches are also presented. The talk concludes with a vision for the future in which bespoke robots can be automatically created for a given task.
Bio:
Josie Hughes completed her Undergraduate, Masters and PhD at the University of Cambridge. She completed her PhD in 2018, developing robots which utilize embodied mechanics and sensory coordination for advanced capabilities. Her research focused on manipulation, sensor technologies and new approaches for designing and fabricating complex anthropomorphic manipulators. Josie is now working as a Post-Doctoral Research Associate in the Distributed Robotics Lab, MIT. At MIT she is working on computational design methods, wearable technologies and new novel robot fabrication methods. Her work has been published in Science Robotics, Nature Machine Intelligence, Soft Robotics and many other conferences and journals. Additionally, she has lead teams which have won over 5 International Robotics Competitions.
Automating the design and creation of complex robots is challenging due to the complexity of the design search space and physical processes required. To address this, data-driven approaches are required to understand how to design and optimize robotic structures for a given task. This talk introduces a number of techniques and processes for the computational design of robots, focusing on automated design, rapid fabrication, and task-specific learning. This includes approaches ranging from biologically inspired design, to developing terrain optimized robots by searching over 10,000s of possible designs, and Bayesian based approaches for rapid task learning. Different application scenarios for these approaches are also presented. The talk concludes with a vision for the future in which bespoke robots can be automatically created for a given task.
Bio:
Josie Hughes completed her Undergraduate, Masters and PhD at the University of Cambridge. She completed her PhD in 2018, developing robots which utilize embodied mechanics and sensory coordination for advanced capabilities. Her research focused on manipulation, sensor technologies and new approaches for designing and fabricating complex anthropomorphic manipulators. Josie is now working as a Post-Doctoral Research Associate in the Distributed Robotics Lab, MIT. At MIT she is working on computational design methods, wearable technologies and new novel robot fabrication methods. Her work has been published in Science Robotics, Nature Machine Intelligence, Soft Robotics and many other conferences and journals. Additionally, she has lead teams which have won over 5 International Robotics Competitions.
Practical information
- General public
- Free