Deep reinforcement learning for map-less goal-driven robot navigation

Dobrevski, Matej (avtor), Skočaj, Danijel (avtor)

Mobile robots that operate in real-world environments need to be able to safely navigate their surroundings. Obstacle avoidance and path planning are crucial capabilities for achieving autonomy of such systems. However, for new or dynamic environments, navigation methods that rely on an explicit map of the environment can be impractical or even impossible to use. We present a new local navigation method for steering the robot to global goals without relying on an explicit map of the environment. The proposed navigation model is trained in a deep reinforcement learning framework based on Advantage Actor–Critic method and is able to directly translate robot observations to movement commands. We evaluate and compare the proposed navigation method with standard map-based approaches on several navigation scenarios in simulation and demonstrate that our method is able to navigate the robot also without the map or when the map gets corrupted, while the standard approaches fail. We also show that our method can be directly transferred to a real robot.

• Jezik: Angleški jezik
• Ključne besede: mobile robotics, reinforcement learning, navigation, deep learning
• Vrsta gradiva: Članek v reviji
• Tipologija: 1.01 - Izvirni znanstveni članek
• Organizacija: FRI - Fakulteta za računalništvo in informatiko
• Status publikacije: Objavljeno
• Različica publikacije: Objavljena publikacija
• Leto izida: 2021
• Št. strani: 13 str.
• Številčenje: Vol. 18, iss. 1
• PID: 20.500.12556/RUL-144122
• UDK: 007.52:004.8
• ISSN pri članku: 1729-8814
• DOI: 10.1177/1729881421992621
• COBISS.SI-ID: 60005379
• Datum objave v RUL: 01.02.2023

Gradivo je del revije

• Naslov: International journal of advanced robotic systems
• Skrajšan naslov: Int. j. adv. robot. syst.
• Založnik: SAGE
• ISSN: 1729-8814
• COBISS.SI-ID: 9061716

Licence

• Licenca: CC BY 4.0, Creative Commons Priznanje avtorstva 4.0 Mednarodna
• Povezava: http://creativecommons.org/licenses/by/4.0/deed.sl
• Opis: To je standardna licenca Creative Commons, ki daje uporabnikom največ možnosti za nadaljnjo uporabo dela, pri čemer morajo navesti avtorja.

Sekundarni jezik

• Jezik: Slovenski jezik
• Ključne besede: mobilna robotika, spodbujevalno učenje, navigacija, globoko učenje

Projekti

• Financer: ARRS - Agencija za raziskovalno dejavnost Republike Slovenije
• Številka projekta: J2-9433
• Naslov: Iskanje nekonsistentnosti v kompleksnih slikovnih podatkih z globokim učenjem

• Financer: ARRS - Agencija za raziskovalno dejavnost Republike Slovenije
• Številka projekta: P2-0214
• Naslov: Računalniški vid