An official website of the United States government
A swarm of unmanned aerial vehicles (UAVs) can be used for many applications, including disaster relief, search and rescue, and establishing communication networks, due to its mobility, scalability, and robustness to failure. However, a UAV swarm’s performance is typically limited by each agent’s stored energy. Recent works have considered the usage of thermals, or vertical updrafts of warm air, to address this issue. One challenge lies in a swarm of UAVs detecting and taking advantage of these thermals. Inspired by hawks, a swarm could take advantage of thermals better than individuals due to the swarm’s distributed sensing abilities. To determine which emergent behaviors increase survival time, simulation software was created to test the behavioral models of UAV gliders around thermals. For simplicity and robustness, agents operate with limited information about other agents. The UAVs’ motion was implemented as a Boids model, replicating the behavior of flocking birds through cohesion, separation, and alignment forces. Agents equipped with a modified behavioral model exhibit dynamic flocking behavior, including relative ascension-based cohesion and relative height-based separation and alignment. The simulation results show the agents flocking to thermals and improving swarm survival. These findings present a promising method to extend the flight time of autonomous UAV swarms.
more »
« less
Soaring like a bird via reinforcement learning in the field
Soaring birds often rely on ascending thermal plumes in the atmosphere as they search for prey or migrate across large distances. The landscape of convective currents is turbulent and rapidly shifts on timescales of a few minutes as thermals constantly form, disintegrate, or are transported away by the wind. How soaring birds find and navigate thermals within this complex landscape is unknown. Reinforcement learning can be used to find an effective navigational strategy as a sequence of decisions taken in response to environmental cues. Reinforcement learning was applied to train gliders in the field to autonomously navigate atmospheric thermals. Gliders of two-meter wingspan were equipped with a flight controller that enabled an on-board implementation of autonomous flight policies via precise control over their bank angle and pitch. Learning is severely challenged by a multitude of physical effects and the unpredictability of the natural environment. A navigational strategy was determined solely from the experiences collected over several days in the field using exploratory behavioral policies. Bird-like performance was achieved and several viable biological mechanosensory cues were identified for soaring birds, which are also directly applicable to the development of autonomous soaring vehicles.
more »
« less
- Award ID(s):
- 1735004
- PAR ID:
- 10078614
- Date Published:
- Journal Name:
- 07 Nature
- Volume:
- 562
- ISSN:
- 1260-3368
- Page Range / eLocation ID:
- 236–239
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
ABSTRACT Estimates of movement costs are essential for understanding energetic and life-history trade-offs. Although overall dynamic body acceleration (ODBA) derived from accelerometer data is widely used as a proxy for energy expenditure (EE) in free-ranging animals, its utility has not been tested in species that predominately use body rotations or exploit environmental energy for movement. We tested a suite of sensor-derived movement metrics as proxies for EE in two species of albatrosses, which routinely use dynamic soaring to extract energy from the wind to reduce movement costs. Birds were fitted with a combined heart-rate, accelerometer, magnetometer and GPS logger, and relationships between movement metrics and heart rate-derived V̇O2, an indirect measure of EE, were analyzed during different flight and activity modes. When birds were exclusively soaring, a metric derived from angular velocity on the yaw axis provided a useful proxy of EE. Thus, body rotations involved in dynamic soaring have clear energetic costs, albeit considerably lower than those of the muscle contractions required for flapping flight. We found that ODBA was not a useful proxy for EE in albatrosses when birds were exclusively soaring. As albatrosses spend much of their foraging trips soaring, ODBA alone was a poor predictor of EE in albatrosses. Despite the lower percentage of time flapping, the number of flaps was a useful metric when comparing EE across foraging trips. Our findings highlight that alternative metrics, beyond ODBA, may be required to estimate energy expenditure from inertial sensors in animals whose movements involve extensive body rotations.more » « less
-
Faisal, Aldo A (Ed.)Animals display characteristic behavioural patterns when performing a task, such as the spiraling of a soaring bird or the surge-and-cast of a male moth searching for a female. Identifying such recurring sequences occurring rarely in noisy behavioural data is key to understanding the behavioural response to a distributed stimulus in unrestrained animals. Existing models seek to describe the dynamics of behaviour or segment individual locomotor episodes rather than to identify the rare and transient sequences of locomotor episodes that make up the behavioural response. To fill this gap, we develop a lexical, hierarchical model of behaviour. We designed an unsupervised algorithm called “BASS” to efficiently identify and segment recurring behavioural action sequences transiently occurring in long behavioural recordings. When applied to navigating larval zebrafish, BASS extracts a dictionary of remarkably long, non-Markovian sequences consisting of repeats and mixtures of slow forward and turn bouts. Applied to a novel chemotaxis assay, BASS uncovers chemotactic strategies deployed by zebrafish to avoid aversive cues consisting of sequences of fast large-angle turns and burst swims. In a simulated dataset of soaring gliders climbing thermals, BASS finds the spiraling patterns characteristic of soaring behaviour. In both cases, BASS succeeds in identifying rare action sequences in the behaviour deployed by freely moving animals. BASS can be easily incorporated into the pipelines of existing behavioural analyses across diverse species, and even more broadly used as a generic algorithm for pattern recognition in low-dimensional sequential data.more » « less
-
Task and motion planning subject to linear temporal logic (LTL) specifications in complex, dynamic environments requires efficient exploration of many possible future worlds. model‐free reinforcement learning has proven successful in a number of challenging tasks, but shows poor performance on tasks that require long‐term planning. in this work, we integrate Monte Carlo tree search with hierarchical neural net policies trained on expressive LTL specifications. we use reinforcement learning to find deep neural networks representing both low‐level control policies and task‐level ``option policies'' that achieve high‐level goals. our combined architecture generates safe and responsive motion plans that respect theLTL constraints. we demonstrate our approach in a simulated autonomous driving setting, where a vehicle must drive down a road in traffic, avoid collisions, and navigate an intersection, all while obeying rules of the road.more » « less
-
Abstract Uncrewed aerial vehicles are integral to a smart city framework, but the dynamic environments above and within urban settings are dangerous for autonomous flight. Wind gusts caused by the uneven landscape jeopardize safe and effective aircraft operation. Birds rapidly reject gusts by changing their wing shape, but current gust alleviation methods for aircraft still use discrete control surfaces. Additionally, modern gust alleviation controllers challenge small uncrewed aerial vehicle power constraints by relying on extensive sensing networks and computationally expensive modeling. Here we show end-to-end deep reinforcement learning forgoing state inference to efficiently alleviate gusts on a smart material camber-morphing wing. In a series of wind tunnel gust experiments at the University of Michigan, trained controllers reduced gust impact by 84% from on-board pressure signals. Notably, gust alleviation using signals from only three pressure taps was statistically indistinguishable from using six pressure tap signals. By efficiently rejecting environmental perturbations, reduced-sensor fly-by-feel controllers open the door to small uncrewed aerial vehicle missions in cities.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- The DOI is not currently available.
