Cloud robotics is a computing paradigm where compute-constrained robotic platforms (e.g., lightweight UAVs or mobile robots) offload compute tasks to a cloud server with virtually unconstrained computational power [1,2,3,4]. This is particularly advantageous to let robots benefit from sophisticated data processing, such as inference of large machine learning models (e.g, DNN for semantic segmentation), while saving on local compute and battery. The other side of the coin is that transmitting data from robots to the cloud and viceversa can severely congest the network, leading to unacceptable delays when tasks are time-critical, such as in autonomous driving. Therefore, wisely choosing when to offload compute tasks and when to perform data processing locally (on robots) to maximize system performance without incurring large delays is paramount.

This thesis explores the delicate tradeoff discussed above. You will be tasked to learn an effective RL-based policy for compute allocation while considering performance (e.g., classification or detection accuracy), network latency, and consumed energy including robot battery. In particular, you will consider one (or multiple) low-compute, low-accuracy inference models run locally on the robot and a high-accuracy model run at the cloud for image classification and semantic segmentation. However, if you'd like to explore different tasks, they can be discussed with the supervisor before starting the thesis.

This thesis may involve a – possibly remote – collaboration with the Massachusetts Institute of Technology.

[1] Chinchali et al., "Network Offloading Policies for Cloud Robotics: a Learning-based Approach," Autonomous Robots, 2021. Available at https://arxiv.org/pdf/1902.05703

[2] Hu et al., "Cloud Robotics: Architecture, Challenges and Applications," IEEE Network, 2012. Available at https://personal.ntu.edu.sg/wptay/MyPapers/Journals/HuTayWen%20-%20Cloud%20robotics%20architectures%20challenges%20and%20applications.pdf

[3] Nakanoya et al. "Co-design of communication and machine inference for cloud robotics," Autonomous Robots, 2023. Available at https://www.roboticsproceedings.org/rss17/p046.pdf

[4] Liu et al. "RoboEC2: A Novel Cloud Robotic System With Dynamic Network Offloading Assisted by Amazon EC2,"  IEEE Transactions on Automation Science and Engineering, 2024. Available at https://ieeexplore.ieee.org/abstract/document/10347007