logistics

China Post is using AI robots to sort parcels, achieving 1,200 packages per hour and 6.5 million parcels per day at the Guangzhou center, demonstrating the growing real-world application of warehouse robots.

China Post has adopted AI robots for package sorting, with a single unit handling up to 1,200 packages per hour. The Guangzhou center processes an average of 6.5 million packages per day, marking the practical implementation of warehouse robots.

Amazon is deploying physical-world AI agents for logistics and commerce, while Visa invests $1B in Replit to enable seamless payment integration with these agents, betting that agent-driven commerce will dominate by 2027.

The author recounts the difficulties of shipping a laptop to a refugee student in Uganda, including a failed attempt via Australia Post due to lithium battery restrictions, and the ongoing process with a freight service.

Zipline has completed over 2 million autonomous drone deliveries, far surpassing competitors, by starting with emergency blood delivery in Rwanda. The company is now expanding rapidly in the US and Africa, with partnerships including Walmart and Chipotle, and a new quiet drone system.

Amazon launches Amazon Supply Chain Services, opening its multimodal freight, automated warehousing, and last-mile delivery network to all businesses. The move follows Amazon's pattern of turning internal cost centers into external services, as it did with Marketplace and AWS.

Zipline showcases next-generation drone infrastructure resembling a robotic hive for delivery services.

This paper proposes a unified knowledge-embedded reinforcement learning framework for generalized capacitated vehicle routing problems, combining route-first cluster-second heuristics with dynamic programming to achieve superior solution quality and strong generalization across diverse variants.

Loop, a logistics AI company, raised a $95M Series C, signaling a shift in supply chain AI investment away from copilots and toward autonomous execution in high-frequency workflows like freight audit and replenishment.

Researchers from MIT and Symbotic developed a deep reinforcement learning system that optimizes robot traffic in autonomous warehouses, achieving a 25% throughput gain over existing methods by dynamically prioritizing robots to avoid congestion.