Browse Topic: Automation
Dufour Aerospace designs and manufactures an automated tilt-wing aircraft for critical cargo delivery missions. Emphasizing operational efficiency, the platform integrates path generation and tracking techniques tailored for the unique dynamics of tilt-wing flight and builds upon the existing lower level control. While there exist a myriad of methods for high-level aircraft automation ranging from PID to MPC, they often require a trade-off between complexity and the capability to handle non-linear dynamics of the system they are controlling. Hence, a lightweight, deterministic geometric path generation approach using clothoid-based transitions between three waypoints and a robust SO(3)- based path tracking controller adapted for tilt-wing dynamics are presented. Additionally, a high-level automation framework is introduced that includes failure mode handling for GNSS loss and communication breakdowns. This system ensures mission continuity and operational safety while supporting flexible mission planning. The methods are validated through extensive flight testing on both small and large-scale aircraft. The latter prove the scalability, safety, and reliability of the presented solution for tilt-wing aircraft automation and enhance the aircraft's capabilities in real-world emergency response and complex operational scenarios.
The Autoclave processing is commonly used in manufacturing high-performance fibre-reinforced thermoset composite components in the aerospace industry. Variations in the cure cycle, sometimes even apparently minor deviations from the prescribed cure cycle, can harm the laminate properties. Given the costly and time-consuming autoclave manufacturing process, there is a strong need to cure the maximum number of parts in the shortest possible time without compromising quality. In order to achieve high-rate automated manufacturing with the optimized autoclave process, it is important to construct a digital twin modelling approach to mirror the physical composite curing process in the virtual domain based on the integration of high-fidelity multi-physics models. The resulting digital twin includes a thermal CFD model, a thermo-chemo-mechanical module, and an efficient and accurate block coupling between these two modules. The customized Abaqus driven by local and spatial variation of the turbulence-induced heat transfer coefficient (HTC) imposed through one-way coupling determines the thermo-mechanical response in composite parts. Using the developed digital twin tool (SMARTCLAVE), HTC's spatial and temporal variation can be generated digitally without invoking an expensive and time-consuming experimental approach. The predicted local boundary conditions are used in SMARTCLAVE to determine the cure kinetics, temperature distribution, and thermal-mechanical response that drives the residual stress and distortion of composite parts after curing. The accuracy of the digital twin for autoclaving is demonstrated first using a benchmark problem followed by the capability demonstration with a single-part L-beam assembly. The benefits of using the digital twin tool are illustrated via the optimal placement of multiple parts in an autoclave to balance the throughput and quality.
ABSTRACT
In this work, we present a lightweight pipeline for robust behavioral cloning of a human driver using end-to-end imitation learning. The proposed pipeline was employed to train and deploy three distinct driving behavior models onto a simulated vehicle. The training phase comprised of data collection, balancing, augmentation, preprocessing, and training a neural network, following which the trained model was deployed onto the ego vehicle to predict steering commands based on the feed from an onboard camera. A novel coupled control law was formulated to generate longitudinal control commands on the go based on the predicted steering angle and other parameters such as the actual speed of the ego vehicle and the prescribed constraints for speed and steering. We analyzed the computational efficiency of the pipeline and evaluated the robustness of the trained models through exhaustive experimentation during the deployment phase. We also compared our approach against state-of-the-art implementation in order to comment on its validity.
This concept for an Aeronautical Design Standard for autonomous systems is methodology to determine the acceptable level of supervision for autonomy in military systems. The level of autonomy is directly related to the level of supervision required for the trust in the autonomous system functionality. The approach defines representative Autonomous Task Elements (ATEs), operational considerations, and levels of autonomy. Each ATE is characterized by an objective, description, and performance standards. Performance standards are expressed as metrics related to the trust in the autonomous behavior and the system’s capability to conduct the ATE. The capability of the autonomous system to meet performance standards is expressed as risk. This risk is compared to specified operational / allowable limits. The corresponding acceptable level of autonomy for the ATE is then determined using the probability of failure to meet the limits. The approach for this concept autonomy ADS parallels ADS 33E-PRF for the assignment of Levels of Handling Qualities based on measurable flight performance characteristics.
A deep-learning powered single-strained electronic skin sensor can capture human motion from a distance. The single strain sensor placed on the wrist decodes complex five-finger motions in real time with a virtual 3D hand that mirrors the original motions. The deep neural network boosted by rapid situation learning (RSL) ensures stable operation regardless of its position on the surface of the skin.
Items per page:
50
1 – 50 of 1240