ICAT: indoor connected autonomous testbed

Indoor autonomous driving testbeds have emerged to complement expensive outdoor testbeds and virtual simulations. We introduce the Indoor Connected Autonomous Testbed (ICAT) for vehicle computing, a platform that not only tackles the unique challenges of indoor autonomous driving, but offers scalable and cost-effective solutions for research in navigation, traffic optimization, and swarm intelligence.

Recent Visitors

We have visitors from various industry leaders and academic institutions. From the industry, we have representatives from Dell, Red Hat, Cisco, Weichai, and Toyota

From the academic sector, we are joined by Professor Kang Shin from the University of Michigan, Professor Engin Kirda from Northeastern University, and Professor Suman Banerjee from the University of Wisconsin-Madison.

Multi-agent  & C-V2X

Panoptic view of ICAT platform in the real world. ICAT is 6 by 5 meters in size, and 10 intelligent robots are used in ICAT now for autonomous driving studies. Heterogeneous computing devices are equipped for Federated Machine Learning (FedML) research and multi-agent vehicle computing

Traffic lights and signs are now integrated seamlessly with C-V2X technologies and enable interactions with traffic agents. Leveraging a down-scaled infrastructure system, multiple traffic signs and traffic lights are set up for realistic traffic simulations, where the traffic signs include speed limit, yield sign, construction zone, stop sign, and do not enter signs.

Digital twin 

Digital twin system of ICAT. (a) ICAT's map is designed within RoadRunner, which is a 3D interactive autonomous driving system builder. (b) The designed map then can be seamlessly imported into CARLA simulations. (c) SUMO simulations are also enabled with the ICAT road system. The merits of leveraging a digital twin for our proposed ICAT platform can be summarized in three aspects. 

Centralized & Decentralized Autonomous Driving

An ICAT centralized multi-agent traffic management system testing in a Python simulation, where simulated 10 traffic agents could be controlled by a centralized planning algorithm to avoid collisions and improve the throughput. The planned trajectories for different robots are marked in different colors. The simulation can be transferred to a ROS-based real-world experiment without extra effort.

An illustration of ROS-based traffic management real-world experiments. (a) 4 robots are running a ROS-based traffic management demo. (b) Real-world demos can be also monitored in RViz, where the ICAT road is published as a Path message (the tilted lines are caused by the automatic connection of section start and end points in the Path message), the planned car trajectories from the central manager are rendered as different colors. (c) We have tested up to 6 robots in the ICAT real-world traffic system.

Decentralized Autonomous Driving differs from traffic management methods in that it doesn't rely on externally received command information, the traffic agents solely rely on their own sensors and computing devices to conduct perception and data processing. Thanks to heterogeneous on-board computing devices, the ICAT robots with ARM computing platforms leverage Scalable Open Architecture For the Embedded Edge (SOAFEE) and Autoware OpenAD Kit to support autonomous driving. SOAFEE and OpenAD Kit serve as a baseline for autonomous driving and enable researchers to quickly and easily modify the perception, planning, and control algorithms. 

Vehicle Computing & Multi-user management

The ICAT platform implements an innovative integration of vehicle computing and multi-user management. As vehicle computing power is increasing rapidly, vehicles can serve as mobile computing platforms for various tasks. Adapting such an idea, our platform harnesses a fleet of 10 sophisticated robots with heterogeneous computing devices including Nvidia Nano, TX2, and NX. Each robot serves a dual purpose for computing: participating in a dynamic traffic system and acting as a resource for distributed computing tasks, such as Federated Machine Learning (FedML). Docker environments for multi-user purposes are set up to improve data privacy and security

HyDRA-T Intelligent robot

We developed a next-generation autonomous robot car platform, Hydra-T, suitable for experiments in the ICAT environment. To facilitate accurate sensing, the environment information can be extracted from both an accurate industry-level 2D-LiDAR, and an Intel RealSence depth camera. Combined with a 9-DOF IMU, the accuracy of localization and pose estimation can be further enhanced. Supporting intensive vehicle computation for multi-purposes, the robot is designed to adapt an Nvidia Orin machine that provides a powerful online machine inference capability. An auto-recharge docking device is built-in to improve the temporal-energy efficiency.