This thesis enhances the autonomy of the M4 (Multi-Modal Mobility Morphobot) robot, designed for Mars and rescue missions. The research enables the robot to autonomously select its locomotion mode and path in complex terrains. Focusing on walking and flying modes, a Gazebo simulation, and custom perception-navigations pipelines are developed. Leveraging deep learning, the robot determines optimal mode transitions based on a 2.5D map. Additionally, an energy efficient path planner based on 2.5D mapping is implemented and validated in simulations. The contributions demonstrate scalability for future mode integrations. The M4 robot showcases intelligent mode switching, efficient navigation, and reduced energy consumption, bringing us closer to fully autonomous multi-modal robots for exploration and rescue missions. This work paves the way for future advancements in autonomous robotics, with the ultimate vision of deploying the M4 robot for exploration and rescue tasks, making a significant impact in the quest for intelligent and versatile robotic systems.

翻译：本论文增强了专为火星探测与救援任务设计的M4（多模式移动形态机器人）的自主性。研究使机器人能够在复杂地形中自主选择运动模式与路径。聚焦于行走与飞行模式，开发了Gazebo仿真环境及定制化感知-导航流水线。借助深度学习技术，机器人基于2.5维地图确定最优模式切换策略。此外，基于2.5维地图的能量高效路径规划器得以实现并通过仿真验证。研究成果展现了未来模式扩展的可扩展性。M4机器人展示了智能模式切换、高效导航及降低能耗的能力，使全自主多模式机器人更接近探索与救援任务的实际应用。本研究为自主机器人技术的未来进步铺平道路，其最终愿景是将M4机器人部署于探索与救援任务中，为追求智能多功能机器人系统做出重要贡献。