#Autonomous Navigation (19)

A3 Ultra navigates floors to tidy rooms

@AGIBOTofficial · 57 views · 2026-11-02

Obstacle-Aware Autonomous Coverage and Navigation for Outdoor Robots

Long-duration outdoor coverage with autonomous platforms remains challenging beyond classical planning: deployments face localization drift in open spaces, obstacles in cluttered sites, controller feasibility in turn-heavy maneuvers, and persistent autonomy with energy management. We propose a unified ROS 2 architecture for single-robot outdoor coverage: a dual-antenna RTK-GNSS fused in an EKF keeps both position and heading accurate across long missions; three controller-aware refinements extend a mature coverage planner; a Nav2-based behavior-tree mission executive coordinates multi-goal execution, layered recovery, cost-aware goal management, and autonomous docking for return-to-charge. In real-world trials across five outdoor areas with varying geometries and obstacle densities, the robot completed every coverage route, sweeping 93.1% to 96.1% of the planned coverage area.

Leonardo Gargani, Matteo Frosi, Matteo Matteucci · 150 views · Sep 1, 2026

Outdoor RobotsCoverage Path Planning

Sep 1, 2026

1:00

evoBOT: Inverted-Pendulum Logistics Robot

@circuitrobotics · 211 views · 2024-11-28

Mobile robotsLogistics Robotics

1:00

RT-SAFE: real-time embodied-agent safety benchmarking

@XTRose88 · 718 views · 2026-10-06

Embodied AISafety Evaluation

Wheels + Legs + Hierarchical RL: Behind ETH Zurich's 8.3 km Autonomous Delivery

A complete wheeled-legged system from ETH Zurich's Robotic Systems Lab (Science Robotics): the low-level locomotion policy, trained by privileged learning (PPO teacher, GRU student imitation) with CPG gait primitives and the state estimator removed, switches autonomously between driving, trotting, and knee-crawling, peaking at 5.0 m/s on flat ground; the high-level navigation policy outputs bounded Beta-distributed velocity commands at 10 Hz, consuming the LLC hidden state and a visited-position buffer for exploration. Trained in WFC procedurally generated navigation worlds with dynamic obstacles, it completed an 8.3 km delivery across Zurich's Glattpark with minimal intervention; in point-goal comparison it was the only method with zero collisions, planned in 0.34 ms (~3 orders of magnitude faster), and achieved a mechanical COT of 0.16 (53% lower, 3x faster than ANYmal).

Lee, Joonho, Bjelonic, Marko, Reske, Alexander · 583 views · May 3, 2024

Wheeled-Leggedhierarchical RL

May 3, 2024