SRA-CP: Risk-Aware Car-to-Car Perception That Shares Only What Matters

Kari Jaaskelainen

24 Nov 2025 — 1 min read

Today’s cooperative perception lets connected cars see around corners by sharing sensor data—but it often floods the airwaves with non-critical info and assumes fixed partners. SRA-CP fixes both.

Risk-aware: Each car detects occlusion-driven blind zones that threaten its current driving task.
Spontaneous and selective: Vehicles broadcast tiny coverage summaries, then trigger targeted sharing only when needed.
Smart teaming: The ego car picks peers that best cover the blind zone.
Bandwidth-savvy fusion: Exchanges prioritize safety-critical objects and adapt to bandwidth limits.

Results: On a public dataset, SRA-CP keeps safety-critical detection within <1% of full generic CP while using only ~20% of the bandwidth, and improves performance by 15% over selective CP methods without risk awareness.

Why it matters: scalable V2X perception that boosts safety in dynamic traffic without overwhelming networks.

Paper: https://arxiv.org/abs/2511.17461v1 • Authors: Jiaxi Liu, Chengyuan Ma, Hang Zhou, Weizhe Tang, Shixiao Liang, Haoyang Ding, Xiaopeng Li, Bin Ran

Paper: https://arxiv.org/abs/2511.17461v1

Register: https://www.AiFeta.com

#AutonomousDriving #V2X #CooperativePerception #ConnectedVehicles #AI #Safety #Robotics #EdgeAI

Meet GRACE: a moral governor for safer, more transparent AI

AI agents are getting powerful—so how do we make sure they do the right thing, not just the effective thing? Meet GRACE, a reason-based moral governor that keeps AI behavior aligned with human norms by separating moral reasoning from goal-driven decision-making. * Moral Module: uses deontic logic and explicit reasons

Why some fine-tuned LLMs miss phishing—and how to fix it

Not all fine-tuned LLMs spot phishing equally. A new study tests Llama 3.1 8B, Gemma 2 9B, and Mistral on high-stakes phishing detection—and uses SHAP and mechanistic interpretability to reveal why models do (or don’t) generalize. * Architecture × data diversity matters: Gemma 2 9B hits state-of-the-art performance (F1

AI that explains itself—by following the science

AI that explains itself—by following the science Black-box AI can be powerful, but it often can’t tell us why it made a decision. Concept Bottleneck Models (CBMs) try to fix that by predicting human-understandable concepts first, then the final answer. The catch: standard CBMs ignore domain-specific cause-and-effect and

Meet GenomAgent: A Team of AI Specialists for Smarter Genomics Q&A

TL;DR: Finding reliable answers in genomics is hard. GenomAgent turns one big AI into a coordinating team of specialists—and beats the current leader by 12% on a key benchmark. Genomic facts live across many databases. Standard chatbots struggle because they can’t flexibly query those sources. GeneGPT added

Cars that share only what matters

Read more

Meet GRACE: a moral governor for safer, more transparent AI

Why some fine-tuned LLMs miss phishing—and how to fix it

AI that explains itself—by following the science

Meet GenomAgent: A Team of AI Specialists for Smarter Genomics Q&A