Vision is an essential part of attitude control for many flying animals, some of which have no dedicated sense of gravity. Flying robots, on the other hand, typically depend heavily on accelerometers and gyroscopes for attitude stabilization. In this work, we present the first vision-only approach to flight control for use in generic environments. We show that a quadrotor drone equipped with a downward-facing event camera can estimate its attitude and rotation rate from just the event stream, enabling flight control without inertial sensors. Our approach uses a small recurrent convolutional neural network trained through supervised learning. Real-world flight tests demonstrate that our combination of event camera and low-latency neural network is capable of replacing the inertial measurement unit in a traditional flight control loop. Furthermore, we investigate the network's generalization across different environments, and the impact of memory and different fields of view. While networks with memory and access to horizon-like visual cues achieve best performance, variants with a narrower field of view achieve better relative generalization. Our work showcases vision-only flight control as a promising candidate for enabling autonomous, insect-scale flying robots.

Achieving human-like dexterity is a longstanding challenge in robotics, in part due to the complexity of planning and control for contact-rich systems. In reinforcement learning (RL), one popular approach has been to use massively-parallelized, domain-randomized simulations to learn a policy offline over a vast array of contact conditions, allowing robust sim-to-real transfer. Inspired by recent advances in real-time parallel simulation, this work considers instead the viability of online planning methods for contact-rich manipulation by studying the well-known in-hand cube reorientation task. We propose a simple architecture that employs a sampling-based predictive controller and vision-based pose estimator to search for contact-rich control actions online. We conduct thorough experiments to assess the real-world performance of our method, architectural design choices, and key factors for robustness, demonstrating that our simple sampling-based approach achieves performance comparable to prior RL-based works. Supplemental material: https://caltech-amber.github.io/drop.

Gyroscopes are crucial for accurate angular velocity measurements in navigation, stabilization, and control systems. MEMS gyroscopes offer advantages like compact size and low cost but suffer from errors and inaccuracies that are complex and time varying. This study leverages machine learning (ML) and uses multiple signals of the MEMS resonator gyroscope to improve its calibration. XGBoost, known for its high predictive accuracy and ability to handle complex, non-linear relationships, and MLP, recognized for its capability to model intricate patterns through multiple layers and hidden dimensions, are employed to enhance the calibration process. Our findings show that both XGBoost and MLP models significantly reduce noise and enhance accuracy and stability, outperforming the traditional calibration techniques. Despite higher computational costs, DL models are ideal for high-stakes applications, while ML models are efficient for consumer electronics and environmental monitoring. Both ML and DL models demonstrate the potential of advanced calibration techniques in enhancing MEMS gyroscope performance and calibration efficiency.

Abstract--In this paper we show the application of the new robotic multi-platform system HSURF to a specific use case of teleoperation, aimed at monitoring and inspection. The HSURF system, consists of 3 different kinds of platforms: floater, sinker and robotic fishes. The collaborative control of the 3 platforms allows a remotely based operator to control the fish in order to visit and inspect several targets underwater following a complex trajectory. A shared autonomy solution shows to be the most suitable, in order to minimize the effect of limited bandwidth and relevant delay intrinsic to acoustic communications. The control architecture is described and preliminary results of the acoustically teleoperated visits of multiple targets in a testing pool are provided.

In recent years, interplanetary exploration has gained significant momentum, leading to a focus on the development of launch vehicles. However, the critical technology of edl mechanisms has not received the same level of attention and remains less mature and capable. To address this gap, we took advantage of the REXUS program to develop a pioneering edl mechanism. We propose an alternative to conventional, parachute based landing vehicles by utilizing autorotation. Our approach enables future additions such as steerability, controllability, and the possibility of a soft landing. To validate the technique and our specific implementation, we conducted a sounding rocket experiment on REXUS29. The systems design is outlined with relevant design decisions and constraints, covering software, mechanics, electronics and control systems. Furthermore, an emphasis will also be the organization and setup of the team entirely made up and executed by students. The flight results on REXUS itself are presented, including the most important outcomes and possible reasons for mission failure. We have not archived an autorotation based landing, but provide a reliable way of building and operating such vehicles. Ultimately, future works and possibilities for improvements are outlined. The research presented in this paper highlights the need for continued exploration and development of edl mechanisms for future interplanetary missions. By discussing our results, we hope to inspire further research in this area and contribute to the advancement of space exploration technology.

Inertial navigation systems (INS) are widely used in both manned and autonomous platforms. One of the most critical tasks prior to their operation is to accurately determine their initial alignment while stationary, as it forms the cornerstone for the entire INS operational trajectory. While low-performance accelerometers can easily determine roll and pitch angles (leveling), establishing the heading angle (gyrocompassing) with low-performance gyros proves to be a challenging task without additional sensors. This arises from the limited signal strength of Earth's rotation rate, often overridden by gyro noise itself. To circumvent this deficiency, in this study we present a practical deep learning framework to effectively compensate for the inherent errors in low-performance gyroscopes. The resulting capability enables gyrocompassing, thereby eliminating the need for subsequent prolonged filtering phase (fine alignment). Through the development of theory and experimental validation, we demonstrate that the improved initial conditions establish a new lower error bound, bringing affordable gyros one step closer to being utilized in high-end tactical tasks.

The problem of classifying turbulent environments from partial observation is key for some theoretical and applied fields, from engineering to earth observation and astrophysics, e.g. to precondition searching of optimal control policies in different turbulent backgrounds, to predict the probability of rare events and/or to infer physical parameters labelling different turbulent set-ups. To achieve such goal one can use different tools depending on the system's knowledge and on the quality and quantity of the accessible data. In this context, we assume to work in a model-free setup completely blind to all dynamical laws, but with a large quantity of (good quality) data for training. As a prototype of complex flows with different attractors, and different multi-scale statistical properties we selected 10 turbulent 'ensembles' by changing the rotation frequency of the frame of reference of the 3d domain and we suppose to have access to a set of partial observations limited to the instantaneous kinetic energy distribution in a 2d plane, as it is often the case in geophysics and astrophysics. We compare results obtained by a Machine Learning (ML) approach consisting of a state-of-the-art Deep Convolutional Neural Network (DCNN) against Bayesian inference which exploits the information on velocity and enstrophy moments. First, we discuss the supremacy of the ML approach, presenting also results at changing the number of training data and of the hyper-parameters. Second, we present an ablation study on the input data aimed to perform a ranking on the importance of the flow features used by the DCNN, helping to identify the main physical contents used by the classifier. Finally, we discuss the main limitations of such data-driven methods and potential interesting applications.

A distant space rock called Bennu is spinning faster meaning its rotation period is getting shorter by about one second every 100 years - but scientists are still trying to figure out why. NASA is observing the asteroid to help them understand the evolution of other similar objects, their potential threat to Earth, and if they could be mined for resources. Scientists used data gathered during the OSIRIS-REx mission, before the probe's arrival, to calculate that Bennu's rotation rate is speeding up over time. Bennu is 70 million miles (110m km) away from Earth. As it moves through space at about 63,000 miles per hour (101,000 km per hour), it also spins, completing a full rotation every 4.3 hours.

The Expanse should just change their post credits for each episode to include a list of homework questions. Seriously--there are so many great things to explore in this hard science fiction show. In a recent episode, one of the large spaceships (the Navoo) rotates in order to create artificial gravity (that's not really a spoiler). Let me get right to it. You are probably somewhere near the surface of the Earth and there is a gravitational force between you and the Earth pulling you down.

The generalization ability of a neural network depends on the optimization procedure used for training it. For practitioners and theoreticians, it is essential to identify which properties of the optimization procedure influence generalization. In this paper, we observe that prioritizing the training of distinct layers in a network significantly impacts its generalization ability, sometimes causing differences of up to 30% in test accuracy. In order to better monitor and control such prioritization, we propose to define layer-level training speed as the rotation rate of the layer's weight vector (denoted by layer rotation rate hereafter), and develop Layca, an optimization algorithm that enables direct control over it through each layer's learning rate parameter, without being affected by gradient propagation phenomena (e.g. vanishing gradients). We show that controlling layer rotation rates enables Layca to significantly outperform SGD with the same amount of learning rate tuning on three different tasks (up to 10% test error improvement). Furthermore, we provide experiments that suggest that several intriguing observations related to the training of deep models, i.e. the presence of plateaus in learning curves, the impact of weight decay, and the bad generalization properties of adaptive gradient methods, are all due to specific configurations of layer rotation rates. Overall, our work reveals that layer rotation rates are an important factor for generalization, and that monitoring it should be a key component of any deep learning experiment.