The field of robotics is moving towards developing more robust and reliable navigation systems, with a focus on safety and adaptability in uncertain environments. Recent work has highlighted the importance of accurate perception, state estimation, and mapping for safe robotic navigation. Researchers are exploring new approaches to address the challenges posed by odometry drift, terrain variation, and obstacle negotiation. Notable papers in this area include:
- Certifiably-Correct Mapping for Safe Navigation Despite Odometry Drift, which introduces a framework for certifiably-correct mapping that ensures obstacle-free regions are correctly classified despite odometry drift.
- Provably-Safe, Online System Identification, which presents an integrated framework for robotic manipulators to safely identify payload parameters while maintaining operational safety guarantees.
- Active Contact Engagement for Aerial Navigation in Unknown Environments with Glass, which proposes a novel approach for robust autonomous aerial navigation in unknown environments with transparent glass obstacles.