mlsanityData to 7 Oct 2026

AutoPilot: Automating SoC Design Space Exploration for SWaP Constrained Autonomous UAVs

arXiv 2102.02988 ↗First posted 5 Feb 2021cs.RO cs.AI cs.ARcited by 0

Not on the map. Why?

Abstract (arXiv)

Building domain-specific accelerators for autonomous unmanned aerial vehicles (UAVs) is challenging due to a lack of systematic methodology for designing onboard compute. Balancing a computing system for a UAV requires considering both the cyber (e.g., sensor rate, compute performance) and physical (e.g., payload weight) characteristics that affect overall performance. Iterating over the many component choices results in a combinatorial explosion of the number of possible combinations: from 10s of thousands to billions, depending on implementation details. Manually selecting combinations of these components is tedious and expensive. To navigate the cyber-physical design space efficiently, we introduce AutoPilot, a framework that automates full-system UAV co-design. AutoPilot uses Bayesian optimization to navigate a large design space and automatically select a combination of autonomy algorithm and hardware accelerator while considering the cross-product effect of other cyber and physical UAV components. We show that the AutoPilot methodology consistently outperforms general-purpose hardware selections like Xavier NX and Jetson TX2, as well as dedicated hardware accelerators built for autonomous UAVs, across a range of representative scenarios (three different UAV types and three deployment environments). Designs generated by AutoPilot increase the number of missions on average by up to 2.25x, 1.62x, and 1.43x for nano, micro, and mini-UAVs respectively over baselines. Our work demonstrates the need for holistic full-UAV co-design to achieve maximum overall UAV performance and the need for automated flows to simplify the design process for autonomous cyber-physical systems.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 17 of its 71 references that are in the map. First posted on arXiv 5 Feb 2021.

Builds on

17 of 71 references.

References · 17

  1. 2017Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real Worldcited by 1,401
  2. 2016End to End Learning for Self-Driving Carscited by 1,000
  3. 2018QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulationcited by 730
  4. 2018Learning to Drive in a Daycited by 266
  5. 2016CAD2RL: Real Single-Image Flight without a Single Real Imagecited by 227
  6. 2017PRM-RL: Long-range Robotic Navigation Tasks by Combining Reinforcement Learning and Sampling-based Planningcited by 64
  7. 2018A 64mW DNN-based Visual Navigation Engine for Autonomous Nano-Dronescited by 21
  8. 2019Autonomous Navigation via Deep Reinforcement Learning for Resource Constraint Edge Nodes using Transfer Learningcited by 19
  9. 2017Toward Low-Flying Autonomous MAV Trail Navigation using Deep Neural Networks for Environmental Awarenesscited by 17
  10. 2017Fast, Autonomous Flight in GPS-Denied and Cluttered Environmentscited by 17
  11. 2021Apollo: Transferable Architecture Explorationcited by 17
  12. 2018Navion: A 2mW Fully Integrated Real-Time Visual-Inertial Odometry Accelerator for Autonomous Navigation of Nano Dronescited by 14
5 more
  1. 2019Air Learning: A Deep Reinforcement Learning Gym for Autonomous Aerial Robot Visual Navigationcited by 13
  2. 2020A Survey of FPGA-Based Robotic Computingcited by 8
  3. 2019Neuroflight: Next Generation Flight Control Firmwarecited by 4
  4. 2019MAVBench: Micro Aerial Vehicle Benchmarkingcited by 4
  5. 2020HiveMind: A Scalable and Serverless Coordination Control Platform for UAV Swarmscited by 1

Built on by

Not cited yet.