Connected Wise’s technology connects vehicles to infrastructure through the use of machine readable signs
and interpreting encrypted messages from these signs for vehicle’s On-board Equipment (OBE) devices.
In collaboration with the U.S. Department of Transportation (USDOT) through the USDOT SBIR program, Connected Wise has developed a technology that can receive information from signs readable only by machine, and interprets them for connected vehicles' OBE devices. The system is empowered by state-of-the-art machine learning techniques which can classify, detect and recognize different roadway entities.
The availability of connected infrastructure is limited in rural areas due to challenges in providing power and fiber optic cable infrastructure. Unlike urban areas, rural communities lack the budget and infrastructure to support Connected and Automated Vehicle (CAV) technology, and with the large majority of roads in the US being rural, it isn't feasible to implement current practices. To mitigate this problem, Connected Wise's technology will replicate the communication between a Road Side Unit (RSU) and an On-Board Unit (OBU) at both an affordable and cost-efficient price that can be quickly deployed.
There are several different applications for the use of this technology, another being implemented in work zones. Work zones can be unpredictable with GPS's not updating the driver of hazardous road conditions including detours. Below is a sample video of a possible real-world work zone application.
Connected Wise focuses on localization, detecting lanes and roadway users in real-time,
and cyber-security against adversarial attacks.
Connected Wise uses encrypted security patches to help ADS authenticate traffic sign information by matching the distinct pattern on these patches with the associated sign information retrieved from a geo-database. The I2V identifiers on the security patches are generated from one-way SHA-512 cryptographic visual hashing algorithm, which prevents third parties from altering the information on the traffic sign. The camera system integrated in ADS will match the security patch with the associated I2V identifier in its local geo-database when the sign is recognized. If any adversary is present on the sign, the traffic sign classification in ADS will conflict with the matched database information.
Maintenance in a smart and proper way is crucial for the longevity of our infrastructure.
This becomes even more important given the introduction of new, advanced vehicle technologies such as connected vehicles.
An AI-aided machine vision system which can leverage video footage recorded by a locomotive’s forward-facing cameras to detect and report the current state of infrastructure at highway-rail grade crossings. Such innovation will reduce the time and labor for inspections and significantly cut the cost of maintaining the infrastructure. Connected Wise's technological solution is an on-board AI edge device inside the locomotive cab that processes live camera images to analyze the current state of infrastructure (e.g. detects a broken gate arm, damaged pavement markings or missing crossbuck signs).
This AI infrastructure assessment using Mixed-Reality (MR) technology employs state-of-the-art methods and algorithms from interdisciplinary practices. Machine learning is used for crack/spall detection on infrastructures where human-computer interaction concepts are employed for improving assessment performance. MR augments virtual information into the real environment and allows the user to alter the information in real-time. While the inspector performs routine inspection tasks, the AI system integrated into the headset continuously guides the inspector and shows possible defect locations.
Maintaining the highway transport linear-asset infrastructures is, for the most part, a task performed manually.
Being a subjective and labor-intensive process, it is an ideal candidate for automation. Connected Wise has proposed a comprehensive solution
that uses an AI embedded on-board computer vision system and data-driven methods to detect the level of degradation on
linear-assets such as traffic signs, traffic signals, roadway lighting, pavement markings, asphalt and concrete surfaces.