{"id":1938,"date":"2020-05-19T11:11:08","date_gmt":"2020-05-19T11:11:08","guid":{"rendered":"https:\/\/www.rtc.us.es\/?page_id=1938"},"modified":"2020-05-19T11:16:47","modified_gmt":"2020-05-19T11:16:47","slug":"reliar","status":"publish","type":"page","link":"https:\/\/grupo.us.es\/rtclab\/neuromorphic-engineering\/reliar\/","title":{"rendered":"RELIAR"},"content":{"rendered":"

Real-Time Loihi interface for\u00a0Neuromorphic Auditory Sensor and ED-Scorbot<\/h2>\n

In this project we aim to integrate a Neuromorphic Auditory Sensor (NAS) as an input to Loihi and\u00a0connect an event-driven robot to the output of Loihi. These will provide a real-time communication,\u00a0being able to compute audio spiking information (NAS output) in real-time and command a robot at\u00a0the same time with negligible latency. The NAS could be also used in combination with a\u00a0neuromorphic retina, as DVS, for sensor fusion or integration applications in real-time. The output Loihi interface will be done for the event-driven robotic arm ED-Scorbot, available at our lab. Several practical applications could be done, as for example SNN for echolocation testing, for speaker identification, speech recognition, etc. Results from the SNN implemented in Loihi could be qualified to produce different spiking rate signals at the output that could be used as joint references at the\u00a0spiking PID controllers of the ED-Scorbot.<\/p>\n

\"\"<\/a><\/p>\n

Objectives:<\/strong><\/p>\n

    \n
  1. Develop a specific communication module in HDL for NAS output integration to Loihi.<\/li>\n
  2. Study what we need at physical level (logic levels, clocks synchrony, etc\u2026) for real-time interfacing.<\/li>\n
  3. Do a research visit, if possible, at Intel to learn and interact deeply.<\/li>\n
  4. Implement a specific SDK for Loihi to give support for NAS communication.<\/li>\n
  5. Integrate everything in OpenNAS and NAVIS for user support.<\/li>\n
  6. Develop an HDL interface between Loihi and event-driven robotics.<\/li>\n
  7. Implement in Loihi simple SNN able to produce different frequencies of spiking signals to command different joint angles in the ED-Scorbot.<\/li>\n
  8. Characterize the whole system in terms of latencies and power consumption and compare it to current SOA.<\/li>\n
  9. Make open-source the interface HDL and software.<\/li>\n<\/ol>\n

    Research plan:<\/strong>\u00a0As expressed in next figure, the project is divided in three modules, MOD1 and MOD 2 will be executed\u00a0in parallel to provide input and output interfaces for Loihi. Then, MOD3 will use results from both modules for the development of a practical demonstrator. Special care on documentation and\u00a0disseminations are included in these modules.<\/p>\n

    \"\"<\/a><\/p>\n

    IP<\/strong>: Alejandro Linares Barranco \/ \u00c1ngel Francisco Jim\u00e9nez Fern\u00e1ndez<\/p>\n

    Start date<\/strong>: 30-12-2016
    \nEnd date:<\/strong> 29-12-2020<\/p>\n

    Researchers:<\/strong><\/p>\n

    Gabriel Jim\u00e9nez Moreno
    \nAntonio R\u00edos Navarro
    \nJuan Pedro Dom\u00edguez Morales
    \nDaniel Guti\u00e9rrez Gal\u00e1n
    \nEnrique Pi\u00f1ero Fuentes<\/p>\n

    Related posts:<\/h3>\n