ArXiv TLDR

Frank Kirchner

4 papers · Latest:

Robotics

Right Model, Right Time: Real-Time Cascaded-Fidelity MPC for Bipedal Walking

This paper introduces a real-time cascaded-fidelity MPC for bipedal walking, combining detailed and simplified models to reduce computational complexity.

2605.04607
Machine Learning

Task-specific Subnetwork Discovery in Reinforcement Learning for Autonomous Underwater Navigation

This paper reveals how multi-task RL agents for underwater navigation specialize using only 1.5% of network weights for task differentiation.

2604.21640
Robotics

DINO-Explorer: Active Underwater Discovery via Ego-Motion Compensated Semantic Predictive Coding

DINO-Explorer enables active underwater discovery by using ego-motion compensated semantic predictive coding to detect novel events efficiently.

2604.12933
Robotics

Contextual Multi-Task Reinforcement Learning for Autonomous Reef Monitoring

This paper introduces contextual multi-task reinforcement learning to develop robust and generalizable control policies for autonomous reef monitoring.

2604.12645

📬 Weekly AI Paper Digest

Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.