Technology

Survey of DL-Based LiDAR Super-Resolution For Autonomous Driving (University College London)

Source

SemiEngineering

Published

Feb 25, 2026

TL;DR

AI Generated

University College London researchers published a comprehensive survey on deep learning-based LiDAR super-resolution for autonomous driving. The paper addresses the challenge of expensive high-resolution LiDAR sensors by using deep learning to enhance sparse point clouds from affordable low-resolution sensors. The survey categorizes existing approaches into CNN-based architectures, model-based deep unrolling, implicit representation methods, and Transformer and Mamba-based approaches. Current trends include range image representation, extreme model compression, and real-time inference prioritization for practical deployment. The paper identifies open challenges and future research directions for advancing LiDAR super-resolution technology.

Read Full Article

DARPA calls for proposals for autonomous underwater drones — gov't looking for a small, cheap autonomous sub that can be developed and built quickly

DARPA has issued a call for proposals to develop a small, affordable autonomous underwater drone that can be quickly built and deployed. The program, known as Deep Thoughts, aims to create flexible AUVs using readily available parts with a rapid development timeline. This initiative reflects the military's interest in expanding drone capabilities beyond aerial vehicles to the deep sea. The U.S. government seeks innovative approaches to building autonomous underwater systems to keep pace with evolving technologies and cost-effective solutions in the drone space.

Tom's Hardware•

5 days ago

MIT Technology Review

Three reasons why DeepSeek’s new model matters

DeepSeek's new V4 model is significant for three key reasons. Firstly, it offers high performance at a fraction of the cost of comparable models, making cutting-edge AI capabilities more accessible. Secondly, V4 introduces a new approach to memory efficiency by handling 1 million tokens in its context window, reducing computing power and memory usage significantly. Lastly, V4 marks a shift towards Chinese chip optimization, specifically for Huawei's Ascend chips, challenging the dominance of US chip giant Nvidia and potentially signaling China's progress in building a parallel AI infrastructure.

MIT Technology Review•

6 days ago

SemiEngineering

Advancing Autonomous Fabs

The semiconductor industry is moving towards Autonomous Semiconductor Fabs, driven by increasing process complexity and equipment costs. Preventive maintenance (PM) is now crucial for equipment availability and productivity. PM automation is seen as a key enabler for autonomous semiconductor manufacturing, addressing challenges in large-scale adoption. The industry recognizes the need for PM automation to enhance manufacturing resilience. The white paper emphasizes the importance of system-level transformation in PM automation, requiring coordination across various aspects like equipment design, data infrastructure, and robotics.

SemiEngineering•

2 weeks ago

Empowering Advanced Autonomous-Driving Systems

The article discusses the challenges and advancements in autonomous driving systems, emphasizing the need for a comprehensive approach beyond just software algorithms. It highlights the importance of multiple sensors, redundancy in communication and processing, and system-level safety to prevent single points of failure. Dr. Stefan Poledna from TTTech Auto shares insights on the current state of the autonomous driving market and the architectural analysis required for safe execution. The focus is on creating diverse and redundant systems to ensure the safety and reliability of next-generation autonomous vehicles.

ElectronicDesign•