Seung Jae Lee

Ehsan K. Ardestani, Changkyu Kim, Seung Jae Lee et al.

Deep Learning Recommendation Models (DLRM) are widespread, account for a considerable data center footprint, and grow by more than 1.5x per year. With model size soon to be in terabytes range, leveraging Storage ClassMemory (SCM) for inference enables lower power consumption and cost. This paper evaluates the major challenges in extending the memory hierarchy to SCM for DLRM, and presents different techniques to improve performance through a Software Defined Memory. We show how underlying technologies such as Nand Flash and 3DXP differentiate, and relate to real world scenarios, enabling from 5% to 29% power savings.

Junseok Lee, Xiangyu Wu, Seung Jae Lee et al.

This paper introduces a collision avoidance system for navigating a multicopter in cluttered outdoor environments based on the recent memory-less motion planner, rectangular pyramid partitioning using integrated depth sensors (RAPPIDS). The RAPPIDS motion planner generates collision-free flight trajectories at high speed with low computational cost using only the latest depth image. In this work we extend it to improve the performance of the planner by taking the following issues into account. (a) Changes in the dynamic characteristics of the multicopter that occur during flight, such as changes in motor input/output characteristics due to battery voltage drop. (b) The noise of the flight sensor, which can cause unwanted control input components. (c) Planner utility function which may not be suitable for the cluttered environment. Therefore, in this paper we introduce solutions to each of the above problems and propose a system for the successful operation of the RAPPIDS planner in an outdoor cluttered flight environment. At the end of the paper, we validate the proposed method's effectiveness by presenting the flight experiment results in a forest environment. A video can be found at www.youtube.com/channel/UCK-gErmvZlBODN5gQpNcpsg

Seung Jae Lee, Inkyu Jang, H. Jin Kim

In this paper, we introduce a new quadcopter fail-safe flight solution that can perform the same four controllable degrees-of-freedom flight as a regular multirotor even when a single thruster fails. The new solution employs a novel multirotor platform known as the T3-Multirotor and utilizes a distinctive strategy of actively controlling the center of gravity position to restore the nominal flight performance. A dedicated control structure is introduced, along with a detailed analysis of the dynamic characteristics of the platform that change during emergency flights. Experimental results are provided to validate the feasibility of the proposed fail-safe flight strategy.

Seung Jae Lee, Seung Hyun Kim, H. Jin Kim

In this paper, we introduce a translational force control method with disturbance observer (DOB)-based force disturbance cancellation for precise three-dimensional acceleration control of a multi-rotor UAV. The acceleration control of the multi-rotor requires conversion of the desired acceleration signal to the desired roll, pitch, and total thrust. But because the attitude dynamics and the thrust dynamics are different, simple kinematic signal conversion without consideration of those difference can cause serious performance degradation in acceleration tracking. Unlike most existing translational force control techniques that are based on such simple inversion, our new method allows controlling the acceleration of the multi-rotor more precisely by considering the dynamics of the multi-rotor during the kinematic inversion. By combining the DOB with the translational force system that includes the improved conversion technique, we achieve robustness with respect to the external force disturbances that hinders the accurate acceleration control. mu-analysis is performed to ensure the robust stability of the overall closed-loop system, considering the combined effect of various possible model uncertainties. Both simulation and experiment are conducted to validate the proposed technique, which confirms the satisfactory performance to track the desired acceleration of the multi-rotor.

Peter Morales, Tzofi Klinghoffer, Seung Jae Lee

Haze degrades content and obscures information of images, which can negatively impact vision-based decision-making in real-time systems. In this paper, we propose an efficient fully convolutional neural network (CNN) image dehazing method designed to run on edge graphical processing units (GPUs). We utilize three variants of our architecture to explore the dependency of dehazed image quality on parameter count and model design. The first two variants presented, a small and big version, make use of a single efficient encoder-decoder convolutional feature extractor. The final variant utilizes a pair of encoder-decoders for atmospheric light and transmission map estimation. Each variant ends with an image refinement pyramid pooling network to form the final dehazed image. For the big variant of the single-encoder network, we demonstrate state-of-the-art performance on the NYU Depth dataset. For the small variant, we maintain competitive performance on the super-resolution O/I-HAZE datasets without the need for image cropping. Finally, we examine some challenges presented by the Dense-Haze dataset when leveraging CNN architectures for dehazing of dense haze imagery and examine the impact of loss function selection on image quality. Benchmarks are included to show the feasibility of introducing this approach into real-time systems.