TY - GEN
T1 - Tiny Robot Learning (tinyRL) for Source Seeking on a Nano Quadcopter
AU - Duisterhof, Bardienus P.
AU - Krishnan, Srivatsan
AU - Cruz, Jonathan J.
AU - Banbury, Colby R.
AU - Fu, William
AU - Faust, Aleksandra
AU - de Croon, Guido C.H.E.
AU - Reddi, Vijay Janapa
PY - 2021
Y1 - 2021
N2 - We present fully autonomous source seeking onboard a highly constrained nano quadcopter, by contributing application-specific system and observation feature design to enable inference of a deep-RL policy onboard a nano quadcopter. Our deep-RL algorithm finds a high-performance solution to a challenging problem, even in presence of high noise levels and generalizes across real and simulation environments with different obstacle configurations. We verify our approach with simulation and in-field testing on a Bitcraze CrazyFlie using only the cheap and ubiquitous Cortex-M4 microcontroller unit. The results show that by end-to-end application-specific system design, our contribution consumes almost three times less additional power, as compared to a competitive learning-based navigation approach onboard a nano quadcopter. Thanks to our observation space, which we carefully design within the resource constraints, our solution achieves a 94% success rate in cluttered and randomized test environments, as compared to the previously achieved 80%. We also compare our strategy to a simple finite state machine (FSM), geared towards efficient exploration, and demonstrate that our policy is more robust and resilient at obstacle avoidance as well as up to 70% more efficient in source seeking. To this end, we contribute a cheap and lightweight end- to-end tiny robot learning (tinyRL) solution, running onboard a nano quadcopter, that proves to be robust and efficient in a challenging task.
AB - We present fully autonomous source seeking onboard a highly constrained nano quadcopter, by contributing application-specific system and observation feature design to enable inference of a deep-RL policy onboard a nano quadcopter. Our deep-RL algorithm finds a high-performance solution to a challenging problem, even in presence of high noise levels and generalizes across real and simulation environments with different obstacle configurations. We verify our approach with simulation and in-field testing on a Bitcraze CrazyFlie using only the cheap and ubiquitous Cortex-M4 microcontroller unit. The results show that by end-to-end application-specific system design, our contribution consumes almost three times less additional power, as compared to a competitive learning-based navigation approach onboard a nano quadcopter. Thanks to our observation space, which we carefully design within the resource constraints, our solution achieves a 94% success rate in cluttered and randomized test environments, as compared to the previously achieved 80%. We also compare our strategy to a simple finite state machine (FSM), geared towards efficient exploration, and demonstrate that our policy is more robust and resilient at obstacle avoidance as well as up to 70% more efficient in source seeking. To this end, we contribute a cheap and lightweight end- to-end tiny robot learning (tinyRL) solution, running onboard a nano quadcopter, that proves to be robust and efficient in a challenging task.
UR - http://www.scopus.com/inward/record.url?scp=85114819135&partnerID=8YFLogxK
U2 - 10.1109/ICRA48506.2021.9561590
DO - 10.1109/ICRA48506.2021.9561590
M3 - Conference contribution
SN - 978-1-7281-9078-5
T3 - Proceedings - IEEE International Conference on Robotics and Automation
SP - 7242
EP - 7248
BT - 2021 IEEE International Conference on Robotics and Automation, ICRA 2021
PB - IEEE
T2 - ICRA 2021
Y2 - 30 May 2021 through 5 June 2021
ER -