Researchers have proposed a personalized longitudinal motion planning policy for intelligent vehicles that combines reinforcement learning with imitation learning. The approach is designed to reduce the gap between human driving behavior and automated vehicle decision-making by allowing a vehicle to adapt its longitudinal driving style to a target driver while still meeting performance requirements.

Understanding traffic scenes under adverse conditions such as rain, fog, night-time illumination, and motion blur remains a major challenge for intelligent transportation systems. Researchers at Tsinghua University propose TrafficPerceiver, a multimodal large language model framework that unifies traffic scene understanding and target-oriented segmentation under natural language instructions. By incorporating reinforcement learning based on group-relative policy optimization, the framework improves robustness and interpretability in complex real-world traffic environments.

New research is calling for a fundamental shift in how Australian universities and scientists publish research that draws on Indigenous Knowledges (sum of the understandings, skills, and philosophies developed by Indigenous societies with long histories of interaction with and custodianship of their natural surroundings), warning that current academic practices risk sidelining First Nations authority while benefiting from their expertise.

The study led by Flinders University and the Australian Institute of Marine Science (AIMS), published as a major perspective piece, argues that Indigenous groups must be treated as active partners in research publications — not just contributors acknowledged in footnotes or ‘personal communications’.