HPRM: High-Performance Robotic Middleware for Intelligent Autonomous Systems

Jacky Kwok, Shulu Li, Marten Lohstroh, Edward A. Lee
UC Berkeley
Code arXiv

Real-time autonomous driving simulation comparison using ROS2 and HPRM

Abstract

The rise of intelligent autonomous systems, especially in robotics and autonomous agents, has created a critical need for robust communication middleware that can ensure real-time processing of extensive sensor data. Current robotics middleware like Robot Operating System (ROS) 2 faces challenges with nondeterminism and high communication latency when dealing with large data across multiple subscribers on a multi-core compute platform. To address these issues, we present High-Performance Robotic Middleware (HPRM), built on top of the deterministic coordination language Lingua Franca (LF). HPRM employs optimizations including an in-memory object store for efficient zero-copy transfer of large payloads, adaptive serialization to minimize serialization overhead, and an eager protocol with real-time sockets to reduce handshake latency. Benchmarks show HPRM achieves up to 173x lower latency than ROS2 when broadcasting large messages to multiple nodes. We then demonstrate the benefits of HPRM by integrating it with the CARLA simulator and running reinforcement learning agents along with object detection workloads. In the CARLA autonomous driving application, HPRM attains 91.1% lower latency than ROS2. The deterministic coordination semantics of HPRM, combined with its optimized IPC mechanisms, enable efficient and predictable real-time communication for intelligent autonomous systems.

overhead

Comparison of delay in writing NumPy arrays to shared memory

overhead

Mean latency of broadcast and gather on 4 nodes with different object sizes

overhead

The serialization and deserialization throughput of ROS2 Numpy Package, in-band serialization, and out-of-band serialization

overhead

Dataflow diagram of the autonomous driving application

overhead

Performance of HPRM and ROS2 on the CARLA benchmark

BibTeX

@misc{kwok2024hprmhighperformanceroboticmiddleware,
    title={HPRM: High-Performance Robotic Middleware for Intelligent Autonomous Systems}, 
    author={Jacky Kwok and Shulu Li and Marten Lohstroh and Edward A. Lee},
    year={2024},
    eprint={2412.01799},
    archivePrefix={arXiv},
    primaryClass={cs.RO},
    url={https://arxiv.org/abs/2412.01799}, 
}