Context Aware Optimal Information Selection for Reliable, Resilient, Secure, and Efficient Cooperative Perception

Cooperative perception significantly enhances a vehicle's local field of view by leveraging shared information from nearby vehicles, thus improving overall situational awareness. However, in densely populated environments, cooperative perception can place substantial strain on both communication band-width and computational resources. Such scenarios often result in excessive redundant information, where multiple vehicles repeatedly report the same objects, provide data at unnecessarily high frequencies, or share information irrelevant to the ego vehicle's current context. These issues cumulatively increase computational overhead prior to data fusion and lead to prolonged decision-making times. Therefore, an effective filtering mechanism is necessary to selectively retain only the most informative objects. Higuchi et al. proposed a value anticipation-based Vehicle-to-Vehicle (V2V) communication approach. In their method, the sender evaluates the potential informational value to receivers and, based on real-time network conditions, either defers or cancels transmissions. This ensures that primarily essential information is disseminated to neighboring vehicles. In another related study, Zhou et al. introduced the Augmented Informative Cooperative Perception (AICP) algorithm, which incorporates both a routing mechanism and message filtering at the receiver side. Their algorithm utilizes an informative-ness measure to assess and select messages, optimizing resource use while ensuring relevant data is received. While redundant messaging is typically seen as a problem due to its computational demands, it can also provide significant benefits in enhancing security within V2X communications. Specifically, redundancy can enhance detection of malicious behavior through corroborative data from trustworthy vehicles, thereby improving the security of V2X communications. Lie et al. proposed Misbehavior Detection for Collective Perception Services in Vehicular Communications (MISO-V), which leverages redundancy from received V2X messages to validate incoming perception information. Upon verifying a new message against redundant data, the receiver updates the sender’s trust score based on whether the information is classified as benign or potentially malicious. This updated trust score subsequently guides down-stream tasks in determining whether to integrate or discard information provided by that sender. Balancing redundancy is thus crucial - maintaining an optimal level of redundancy can simultaneously enhance security and sustain computational efficiency. A suitable approach involves dynamically adjusting redundancy based on multiple factors, including source reliability (assessed via trust mechanisms), the planned route of the ego vehicle, prevailing network conditions, and the Age of Information (AoI). This strategy ensures that cooperative perception remains robust, secure, and scalable, supporting accurate and timely decision-making within cooperative vehicle networks. The aim is to establish a balance between purposeful and efficient redundancy and safety against potential attack scenarios, optimizing the use of communicated data and the reliability of data fusion necessary for downstream tasks such as planning and control. The research team will explore information redundancy, perception inconsistencies, context aware fusion, spoofing and other attack scenarios, and the detection of attack patterns and will employ optimization strategies and reinforcement learning techniques. The focus will include intersection scenarios with varying traffic densities and connectivity levels. In addition to using the VeReMi dataset, the team will explore extensions to more realistic collaborative perception message attach scenarios for evaluation and validation.

• Record URL:
  • https://utc.engineering.osu.edu/context-aware-optimal-information-selection-reliable-resilient-secure-and-efficient-cooperative-perception

Language

• English

Project

• Status: Active
• Funding: $120,630.00
• Contract Numbers:

  69A3552348327

• Sponsor Organizations:

  Office of the Assistant Secretary for Research and Technology

  University Transportation Centers Program
  Department of Transportation
  Washington, DC  United States  20590
• Managing Organizations:

  Center for Automated Vehicle Research with Multimodal Assured Navigation

  Ohio State University
  Columbus, OH  United States  43210
• Project Managers:

  Ghasemi, Hamid

• Performing Organizations:

  Ohio State University Center for Automotive Research

  930 Kinnear Road
  Columbus, OH  United States  43212
• Principal Investigators:

  Redmill, Keith

• Start Date: 20260101
• Expected Completion Date: 20260831
• Actual Completion Date: 0
• USDOT Program: University Transportation Centers

Subject/Index Terms

• TRT Terms: Computer security; Connected vehicles; Data fusion; Information processing; Machine learning; Mobile communication systems; Redundancy; Vehicle to vehicle communications
• Subject Areas: Data and Information Technology; Highways; Security and Emergencies; Vehicles and Equipment;

Filing Info

• Accession Number: 01981606
• Record Type: Research project
• Source Agency: Center for Automated Vehicle Research with Multimodal Assured Navigation
• Contract Numbers: 69A3552348327
• Files: UTC, RIP
• Created Date: Mar 2 2026 7:08PM