Vision Based Autonomous Navigation for Unmanned Ground Vehicle for Outdoor environment

Source summary

Develop camera-led autonomous navigation for an outdoor ground vehicle without GPS. Recognise traversable paths and hazards, estimate position/orientation through visual SLAM or odometry and plan around sudden obstacles toward a destination. Deliver a lightweight perception model and planning software translating visual estimates into vehicle motion. Demonstrate collision-free point-to-point travel in varied outdoor conditions; search-and-rescue, agriculture and delivery are example applications rather than exclusive users.