Autonomous Robots Letpub -

L. Chen¹, M. Kowalski², S. Patel¹ ¹Department of Robotics, Tsinghua University, Beijing, China ²Institute of Autonomous Systems, Warsaw University of Technology, Poland

Autonomous Robots (Springer) Status: Submitted – Under Review (LetPub ID: AUTO-2026-0417) Abstract The deployment of autonomous robots in unstructured environments—such as disaster zones, dense forests, or planetary surfaces—requires robust navigation and real-time task allocation under uncertainty. This paper presents a novel modular framework that integrates deep reinforcement learning (DRL) with a dynamic graph-based task scheduler. Unlike end-to-end policies, our system separates perception (LiDAR + RGB), local path planning (SAC algorithm), and global task allocation (Hungarian algorithm with receding horizon). Experiments in both simulation (Habitat 2.0, Gazebo) and physical trials (Clearpath Jackal robots) show a 34% improvement in task completion rate and a 41% reduction in collision frequency compared to baseline DRL methods. Ablation studies confirm the modular design’s generalizability across unseen obstacle densities. We release the code and simulation environment for reproducibility. autonomous robots letpub

Autonomous robots · Deep reinforcement learning · Task allocation · Modular navigation · Unstructured environments 1. Introduction Autonomous robots have transitioned from controlled laboratories to real-world applications: search and rescue, precision agriculture, and underground mining. However, three fundamental challenges persist: (i) partial observability in dynamic environments, (ii) coupling between low-level control and high-level mission planning, and (iii) sample inefficiency of monolithic learning approaches. Experiments in both simulation (Habitat 2