{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T14:50:51Z","timestamp":1784299851561,"version":"3.55.0"},"reference-count":0,"publisher":"Association for the Advancement of Artificial Intelligence (AAAI)","issue":"1","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["AAAI-SS"],"abstract":"<jats:p>Autonomous tiny drones face significant challenges in navigation due to strict constraints on size, weight, power, and onboard computational capacity. This paper presents a lightweight navigation framework that integrates basic multi-sensor perception with deep reinforcement learning (DRL) to enable safe, mapless flight in cluttered environments. We employ the Crazyflie 2.1 nano-drone, equipped with a grayscale camera and a multi-ranger deck, a laser-based distance sensor, for real-time obstacle detection and avoidance. A Proximal Policy Optimization (PPO) agent is trained within a ROS and Gazebo simulation environment to generate collision-free trajectories using fused visual and range data. The system is evaluated in two environments: a simple obstacle field, where the drone achieves a 100% success rate (112\/112 episodes), and a densely cluttered map, where it reaches the target in 35% of trials (7\/20). These results demonstrate that effective autonomous navigation is achievable using minimal sensing and low-computation models, making it well-suited for resource-constrained aerial platforms.<\/jats:p>","DOI":"10.1609\/aaaiss.v7i1.36948","type":"journal-article","created":{"date-parts":[[2025,11,23]],"date-time":"2025-11-23T08:20:02Z","timestamp":1763886002000},"page":"663-669","source":"Crossref","is-referenced-by-count":1,"title":["LiMPNet: Lightweight Multi-sensor Perception and DRL\nNavigation for Tiny Drones in Mapless Environments"],"prefix":"10.1609","volume":"7","author":[{"given":"Omer","family":"Kurkutlu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Arman","family":"Roohi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"9382","published-online":{"date-parts":[[2025,11,23]]},"container-title":["Proceedings of the AAAI Symposium Series"],"original-title":[],"link":[{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI-SS\/article\/download\/36948\/39086","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI-SS\/article\/download\/36948\/39086","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,23]],"date-time":"2025-11-23T08:20:02Z","timestamp":1763886002000},"score":1,"resource":{"primary":{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI-SS\/article\/view\/36948"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,23]]},"references-count":0,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,11,23]]}},"URL":"https:\/\/doi.org\/10.1609\/aaaiss.v7i1.36948","relation":{},"ISSN":["2994-4317"],"issn-type":[{"value":"2994-4317","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,23]]}}}