Search for: All records

In geophysical flows, the presence of sediment in suspension and transport can play an important role in modifying the turbulent properties of the carrier fluid. Much research has focused on the effects of relatively small diameter (less than 1 mm) quartz-density (2.65 g/cm3) particles on turbulent flow. Asian carp is a wide-spread invasive aquatic species in the U.S., causing severe ecological problems in rivers and lakes. Unlike sediment, Asian carp eggs are semi-buoyant particles (~1.05 g/cm3 when initially spawned and ~1.00 g/cm3 in the post-water-hardening period) whose diameter stabilizes to approximately 5 mm. This paper examines how turbulent flow is affected by the presence of particles serving as surrogates for Asian carp eggs as a function of turbulence intensity. Experiments were conducted in a mixing box with the oscillating grid placed near the bottom boundary, and 2D PIV was used to quantify the turbulent characteristics of the carrier fluid. Five paired experiments with and without Asian carp egg surrogate particles were conducted. Results show that under different grid oscillation frequencies (2 to 6 Hz), the mean kinetic energy of the carrier fluid decreased slightly in the presence of the particles, but the turbulent kinetic energy of the fluid did not change appreciably. This suggests strongly that Asian carp eggs in suspension do not modify turbulence intensity of the carrier fluid. These experimental results provide important insight into the entrainment, transport, and deposition of Asian carp eggs, which can inform models to predict the future spread of this invasive species. 

Snow nitrate is vulnerable to photolytic loss that causes isotopic alteration, and thus its isotopes can potentially track the extent of snow nitrate photolysis and its impacts in environments where loss is significant. Large increases in δ¹⁵N‐NO₃⁻below the snow surface have been attributed to photolysis and this behavior is generally consistent amongst theoretical as well as lab and field studies. Oxygen isotope ratios are thought to be influenced by photolysis as well as secondary condensed‐phase chemistry, but the competing effects have yet to be reconciled. Here we use a model that simulates nitrate burial, photolytic fractionation, and re‐oxidation in snow to quantitatively assess these processes with the aim of developing a consistent framework for interpreting the photolytic effects of the complete nitrate isotopic composition (δ¹⁵N, δ¹⁸O, and Δ¹⁷O). This study reveals that isotopic effects of nitrate photolysis and aqueous‐phase re‐oxidation chemistry are important sources of uncertainties in modeling δ¹⁸O‐NO₃⁻.

 

Driven by the expanse of Internet of Things (IoT) and Cyber-Physical Systems (CPS), there is an increasing demand to process streams of temporal data on embedded devices with limited energy and power resources. Among all potential solutions, neuromorphic computing with spiking neural networks (SNN) that mimic the behavior of brain, have recently been placed at the forefront. Encoding information into sparse and distributed spike events enables low-power implementations, and the complex spatial temporal dynamics of synapses and neurons enable SNNs to detect temporal pattern. However, most existing hardware SNN implementations use simplified neuron and synapse models ignoring synapse dynamic, which is critical for temporal pattern detection and other applications that require temporal dynamics. To adopt a more realistic synapse model in neuromorphic platform its significant computation overhead must be addressed. In this work, we propose an FPGA-based SNN with biologically realistic neuron and synapse for temporal information processing. An encoding scheme to convert continuous real-valued information into sparse spike events is presented. The event-driven implementation of synapse dynamic model and its hardware design that is optimized to exploit the sparsity are also presented. Finally, we train the SNN on various temporal pattern-learning tasks and evaluate its performance and efficiency as compared to rate-based models and artificial neural networks on different embedded platforms. Experiments show that our work can achieve 10X speed up and 196X gains in energy efficiency compared with GPU. 

Unmanned aerial vehicle (UAV) technology is a rapidly growing field with tremendous opportunities for research and applications. To achieve true autonomy for UAVs in the absence of remote control, external navigation aids like global navigation satellite systems and radar systems, a minimum energy trajectory planning that considers obstacle avoidance and stability control will be the key. Although this can be formulated as a constrained optimization problem, due to the complicated non-linear relationships between UAV trajectory and thrust control, it is almost impossible to be solved analytically. While deep reinforcement learning is known for its ability to provide model free optimization for complex system through learning, its state space, actions and reward functions must be designed carefully. This paper presents our vision of different layers of autonomy in a UAV system, and our effort in generating and tracking the trajectory both using deep reinforcement learning (DRL). The experimental results show that compared to conventional approaches, the learned trajectory will need 20% less control thrust and 18% less time to reach the target. Furthermore, using the control policy learning by DRL, the UAV will achieve 58.14% less position error and 21.77% less system power. 

A framework for autonomous waypoint planning, trajectory generation through waypoints, and trajectory tracking for multi-rotor unmanned aerial vehicles (UAVs) is proposed in this work. Safe and effective operations of these UAVs is a problem that demands obstacle avoidance strategies and advanced trajectory planning and control schemes for stability and energy efficiency. To address this problem, a two-level optimization strategy is used for trajectory generation, then the trajectory is tracked in a stable manner. The framework given here consists of the following components: (a) a deep reinforcement learning (DRL)-based algorithm for optimal waypoint planning while minimizing control energy and avoiding obstacles in a given environment; (b) an optimal, smooth trajectory generation algorithm through waypoints, that minimizes a combinaton of velocity, acceleration, jerk and snap; and (c) a stable tracking control law that determines a control thrust force for an UAV to track the generated trajectory. 

Continuous trajectory control of fixed-wing unmanned aerial vehicles (UAVs) is complicated when considering hidden dynamics. Due to UAV multi degrees of freedom, tracking methodologies based on conventional control theory, such as Proportional-Integral-Derivative (PID) has limitations in response time and adjustment robustness, while a model based approach that calculates the force and torques based on UAV’s current status is complicated and rigid.We present an actor-critic reinforcement learning framework that controls UAV trajectory through a set of desired waypoints. A deep neural network is constructed to learn the optimal tracking policy and reinforcement learning is developed to optimize the resulting tracking scheme. The experimental results show that our proposed approach can achieve 58.14% less position error, 21.77% less system power consumption and 9:23% faster attainment than the baseline. The actor network consists of only linear operations, hence Field Programmable Gate Arrays (FPGA) based hardware acceleration can easily be designed for energy efficient real-time control.