Max Robotics — Global Service Robot Directory + US Certification

About

Kenneth Oslund is a robotics researcher whose work bridges the gap between machine learning and real-world physical performance. His primary research areas include reinforcement learning, sampling-based motion planning, and high-speed robotic manipulation. Oslund’s most influential contribution is the PRM-RL framework (2018, 23 citations), a hierarchical method that combines probabilistic roadmaps with reinforcement learning to enable long-range navigation in complex environments. This approach allows robots to learn short-range, point-to-point policies that account for dynamics and task constraints without requiring global knowledge, making it a foundational tool for autonomous navigation. More recently, Oslund has made headlines with his work on competitive robot table tennis (2024–2025, 3+ citations), where he and his team developed the first learned robotic agent to achieve amateur human-level performance in this physically demanding sport. This achievement marks a significant milestone in real-time, high-speed manipulation, demonstrating that robots can now match human reflexes and strategy in dynamic, adversarial settings. Oslund’s work continues to push the boundaries of what autonomous systems can accomplish in the physical world.