Creating accurate maps of complex, unknown environments is of utmost importance for truly autonomous navigation robot. However, building these maps online is far from trivial, especially when dealing with large amounts of raw sensor readings on a computation and energy constrained mobile system, such as a small drone. While numerous approaches tackling this problem have emerged in recent years, the mapping accuracy is often sacrificed as systematic approximation errors are tolerated for efficiency's sake. Motivated by these challenges, we propose Voxfield, a mapping framework that can generate maps online with higher accuracy and lower computational burden than the state of the art. Built upon the novel formulation of non-projective truncated signed distance fields (TSDFs), our approach produces more accurate and complete maps, suitable for surface reconstruction. Additionally, it enables efficient generation of Euclidean signed distance fields (ESDFs), useful e.g., for path planning, that does not suffer from typical approximation errors. Through a series of experiments with public datasets, both real-world and synthetic, we demonstrate that our method beats the state of the art in map coverage, accuracy and computational time. Moreover, we show that Voxfield can be utilized as a back-end in recent multiresolution mapping frameworks, producing high quality maps even in large-scale experiments. Finally, we validate our method by running it onboard a quadrotor, showing it can generate accurate ESDF maps usable for real-time path planning and obstacle avoidance.

In-depth training of machine tool (MT) operators is crucial to avoid machine damage due to faulty operation. However, machine-hours are costly and during the training, the MT is unavailable for regular production purposes. Here, virtual real-size models offer a solution by providing basic operation principles to future operators. In this context, it is yet unknown whether a virtual teaching enhanced by real walking is similar to a real teaching scenario regarding the learning efficiency and long-term memory retention. This paper describes a study comparing the learning efficiency of a virtual training session with traditional instructions on a real MT. The learning success of both training groups is objectively and subjectively assessed on a real MT a week later. In this assessment, the task completion time and the number of errors are recorded. We observed that the virtually taught group slightly outperformed trainees taught in reality regarding both objective measurements.

This work presents a pipeline for autonomous emergency landing for multicopters, such as rotary wing Unmanned Aerial Vehicles (UAVs), using deep Reinforcement Learning (RL). Mechanical malfunctions, strong winds, sudden battery life drops (e.g. due to cold weather), failure in localization or GPS jamming are not uncommon and all constitute emergency situations that require a UAV to abort its mission early and land as quickly as possible in the immediate vicinity. To this end, it is crucial for a UAV that is deployed in real missions to be able to detect a safe landing spot efficiently and proceed to land autonomously, avoiding damage to both its integrity and the surroundings. Driven by the advances in semantic segmentation and depth completion using machine learning, the proposed architecture uses deep RL to infer actions from semantic and depth information, flying the robot towards secure areas, while respecting safety constraints. Thanks to our robust training strategy and the choice of these mid-level representations as input to the RL agent, we show that our policy can directly transfer to the real world, without the need for any additional fine-tuning. In a series of challenging experiments both in simulation and with a real platform, we demonstrate that our planner guides a rotorcraft UAV to a safe landing spot up to 1.5 times faster and with double success rate than the state of the art (including a commercially available solution), paving the way towards realistically deployable UAVs.

No abstract

In-depth training of machine tool (MT) operators is crucial to avoid machine damage due to faulty operation. However, machine-hours are costly and during the training, the MT is unavailable for regular production purposes. Here, virtual real-size models offer a solution by providing basic operation principles to future operators. In this context, it is yet unknown whether a virtual teaching enhanced by real walking is similar to a real teaching scenario regarding the learning efficiency and long-term memory retention. This paper describes a study comparing the learning efficiency of a virtual training session with traditional instructions on a real MT. The learning success of both training groups is objectively and subjectively assessed on a real MT a week later. In this assessment, the task completion time and the number of errors are recorded. We observed that the virtually taught group slightly outperformed trainees taught in reality regarding both objective measurements.