Autonomous vehicles learn to cooperate in complex traffic
Peer-Reviewed Publication
Updates every hour. Last Updated: 23-Oct-2026 12:17 ET (23-Oct-2026 16:17 GMT/UTC)
Researchers developed COIN, a collaborative and interaction-aware reinforcement learning framework for multi-agent autonomous driving. COIN enables vehicles to learn both individual navigation and system-level cooperation, improving safety and efficiency in dense scenarios such as intersections, roundabouts, and bottlenecks. The framework was evaluated in simulation and further validated on a hybrid robotic platform.
A mini-review published in the Journal of Bioresources and Bioproducts explores teak-derived quinones as potential redox-active additives for alkaline pulping. Anthraquinone has long been used to promote lignin removal while helping preserve carbohydrates, but safety concerns have encouraged the search for alternatives. By examining studies published between 1972 and 2026, the review compares synthetic anthraquinone derivatives, teak wood extracts and individual compounds such as 2-methylanthraquinone, deoxylapachol and lapachol. The findings suggest that some teak-derived materials can improve delignification, retain carbohydrates or reduce alkali requirements under specific cooking conditions. Nevertheless, differences in extract composition, limited toxicological evidence and the lack of comprehensive process-level assessments remain important barriers to wider application.