Efficient Computing for Autonomous Navigation of Miniaturized Robots
April 2, 2019
3,853
106
3
2.83%
Search the Record
IndexedEvery word spoken in this episode is indexed. Type any phrase to jump straight to the moment it was said.
Type any word or phrase that may have been spoken. Click a result to seek the player to that exact moment.
Try a name, a topic, or a quoted line
Mit Eems Group Pi Vivienne Sze Episodes Around April 2, 2019
See what was published immediately before and after this episode.
1:40FastDepth: Fast Monocular Depth Estimation on Embedded Systems @ ICRA 2019
22:55Now PlayingEfficient Computing for Autonomous Navigation of Miniaturized Robots
YouTube Description
as posted by the channelPresentation at MARS 2019
[This work was done in collaboration with Sertac Karaman and Joel Emer]
While the low-energy, miniature actuation, and sensing systems have already been developed in many cases, the powerful computers that modern artificial intelligence and autonomy depend on are still bulky, heavy and energy-hungry. Vivienne will present breakthrough methods involving the co-design of algorithms and hardware, where the hardware is customized from the ground up to deliver orders of magnitude reductions in power consumption and size, while also increasing processing speed. She will also discuss why this is a critical step towards enabling the smallest fully-autonomous aerial robotic vehicle ever built as well as other innovative robotic use cases.
Works highlighted in this talk include
* Y.H. Chen, T. Krishna, J. Emer, V. Sze, “EyerissAn EnergyEfficient Reconfigurable Accelerator for Deep Convolutional Neural Networks,” IEEE Journal of SolidState Circuits (JSSC), ISSCC Special Issue, Vol. 52, No. 1, pp. 127138, January 2017. [Project website ]
* A. Suleiman, Z. Zhang, L. Carlone, S. Karaman, V. Sze, “NavionA 2mW Fully Integrated RealTime VisualInertial Odometry Accelerator for Autonomous Navigation of Nano Drones,” IEEE Journal of SolidState Circuits (JSSC), VLSI Symposia Special Issue, Vol. 54, No. 4, pp. 11061119, April 2019. [Project website ]
* P. Z. X. Li*, Z. Zhang*, S. Karaman, V. Sze, “High-throughput Computation of Shannon Mutual Information on Chip,” Robotics: Science and Systems (RSS), June 2019.
Guests & Subjects Covered
Sentinel Indexing in Progress
Metadata and chapters are available. Claim extraction for this episode is pending.
All video content is delivered via YouTube embedded players in accordance with the YouTube Terms of Service. Sentinel provides research tools that promote discovery and accountability across political media.