Researcher Tenure Track - Principal Investigator
Neuromorphic technology for robotics
Chiara Bartolozzi is Researcher at the Italian Institute of Technology. She earned a degree in Engineering at University of Genova (Italy) and a Ph.D. in Neuroinformatics at ETH Zurich, developing analog subthreshold circuits for emulating biophysical neuronal properties onto silicon and modelling selective attention on hierarchical multi-chip systems.
She is currently leading the Neuromorphic Systems and Interfaces group, with the aim of applying the "neuromorphic" engineering approach to the design of robotic platforms as enabling technology towards the design of autonomous machines.
This goal is pursued by inducing a paradigm shift in robotics, based on the emerging concept of Event-Driven (ED) sensing and processing. Similarly to their biological counterpart, and differently from traditional robotic sensors, ED sensory systems sample their input signal at fixed (and relative) amplitude changes, intrinsically adapting to the dynamics of the sensory signal: temporal resolution is extremely high for fast transitory signals and decreases for slower inputs.
This approach naturally leads to better robots that acquire, transmit and process information only when needed, optimising the use of resources, leading to real-time, low-cost, operation.
- PhD call is now open! Research themes focus on ED vision for detecting falling objects during manipulation and corrective actions, ED vision and touch for object recognition and manipulation, ED vision for fast control of the robot when interacting with moving objects. Deadline for application: 13th June 2017
- Keynote talk @ ICRA 2017 WS on event-based vision
- VVV17 International Winter School on Humanoid Robot Programming: ED robotics day! Students were challenged with assignment on ED selective attention
- The new eye of the neuromorphic iCub is ready and at work! It features two cameras in each eye: one large field of view ED sensor (ATIS) and one 1.3Mpixels traditional camera from OnSemiconductor
- Event-Driven library and basic computing modules for YARP and iCub available on github
- Ball Tracking @ IROS 2016 finalist of RoboCup Best Paper Award
EcoMode: Event-Driven Compressive Vision for Multimodal Interaction with Mobile Devices (H2020-ICT-RIA-644096, 2015-2018)
eMorph: Event–Driven Morphological Computation for Embodied Systems (STREP-ICT-FET-231467, 2008-2012)
Where and When: Event-Based Spatiotemporal Trajectory Prediction from the iCub's Point-Of-ViewProceedings - IEEE International Conference on Robotics and Automation, pp. 9521-9527
Event-Driven Encoding Algorithms for Synchronous Front-End Sensors in Robotic PlatformsIEEE Sensors Journal, vol. 19, (no. 16), pp. 7149-7161
Proto-object based saliency for event-driven camerasIEEE International Conference on Intelligent Robots and Systems, pp. 805-812
Spike-Based Readout of POSFET Tactile SensorsIEEE Transactions on Circuits and Systems I: Regular Papers, vol. 64, (no. 6), pp. 1421-1431