In the field of robotics, a major challenge is achieving high levels of autonomy with small vehicles that have limited mass and power budgets. The main motivation for designing such small vehicles is that compared to their larger counterparts, they have the potential to be safer, and hence be available and work together in large numbers. One of the key components in micro robotics is efficient software design to optimally utilize the computing power available. This paper describes the computer vision and control algorithms used to achieve autonomous flight with the ∼30g tailless flapping wing robot, used to participate in the International Micro Air Vehicle Conference and Competition (IMAV 2018) indoor microair vehicle competition. Several tasks are discussed: line following, circular gate detection and fly through. The emphasis throughout this paper is on augmenting traditional techniques with the goal to make these methods work with limited computing power while obtaining robust behavior. @en

In the field of robotics, a major challenge is achieving high levels of autonomy with small vehicles that have limited mass and power budgets. The main motivation for designing such small vehicles is that, compared to their larger counterparts, they have the potential to be safer, and hence be available and work together in large numbers. One of the key components in micro robotics is efficient software design to optimally utilize the computing power available. This paper describes the computer vision and control algorithms used to achieve autonomous flight with the _30-gram tailless flapping wing robot, used to participate in the IMAV 2018 indoor micro air vehicle competition. Several tasks are discussed: line following, and circular gate detection and fly-through. The emphasis throughout this paper is on augmenting traditional techniques with the goal to make these methods work with limited computing power while obtaining robust behaviour. @en

In the field of robotics, a major challenge is extending the flight range of micro aerial vehicles. One way to extend the range is by charging batteries with solar arrays on the ground, while resting on intermediate landing positions. The solution we propose in this study differentiates itself from other solutions as it does not focus on improving UAV efficiency but rather on finding the most efficient landing position. In particular, an algorithm is developed to show the usefulness of the approach. This algorithm makes uses of the sonar sensor on board of the Parrot Bebop 1 drone in combination with an OptiTrack system to scan the environment for potential landing opportunities. After these measurements are discretized on a 2D grid, analysis is carried out with a sun position predicting model. Finally, a landing position is chosen within the scanned area and the drone will land accordingly. Little is known on whether a solar powered charge on the ground could be effective in a limited period of time. We present a coarse analysis, showing that the DelftaCopter with solar arrays on its wings charges its batteries in 1.3 days with relatively cheap solar cells in Africa or Australia. Future work includes the use of computer vision instead of sonar as well as the ensurance of a safe landing position using vision. @en

We present fully autonomous source seeking onboard a highly constrained nano quadcopter, by contributing application-specific system and observation feature design to enable inference of a deep-RL policy onboard a nano quadcopter. Our deep-RL algorithm finds a high-performance solution to a challenging problem, even in presence of high noise levels and generalizes across real and simulation environments with different obstacle configurations. We verify our approach with simulation and in-field testing on a Bitcraze CrazyFlie using only the cheap and ubiquitous Cortex-M4 microcontroller unit. The results show that by end-to-end application-specific system design, our contribution consumes almost three times less additional power, as compared to a competitive learning-based navigation approach onboard a nano quadcopter. Thanks to our observation space, which we carefully design within the resource constraints, our solution achieves a 94% success rate in cluttered and randomized test environments, as compared to the previously achieved 80%. We also compare our strategy to a simple finite state machine (FSM), geared towards efficient exploration, and demonstrate that our policy is more robust and resilient at obstacle avoidance as well as up to 70% more efficient in source seeking. To this end, we contribute a cheap and lightweight end- to-end tiny robot learning (tinyRL) solution, running onboard a nano quadcopter, that proves to be robust and efficient in a challenging task.@en