Related papers: Binary Neural Network in Robotic Manipulation: Fle…
In this paper, we perform robot manipulation activities in real-world environments with language contexts by integrating a compact referring image segmentation model into the robot's perception module. First, we propose CLIPU$^2$Net, a…
Previous work has shown that it is possible to train deep neural networks with low precision weights and activations. In the extreme case it is even possible to constrain the network to binary values. The costly floating point…
Recent trends show recognition accuracy increasing even more profoundly. Inference process of Deep Convolutional Neural Networks (DCNN) has a large number of parameters, requires a large amount of computation, and can be very slow. The…
Controlling a high degrees of freedom humanoid robot is acknowledged as one of the hardest problems in Robotics. Due to the lack of mathematical models, an approach frequently employed is to rely on human intuition to design keyframe…
Convolutional neural networks have achieved astonishing results in different application areas. Various methods which allow us to use these models on mobile and embedded devices have been proposed. Especially binary neural networks seem to…
We present a library to automatically embed signal processing and neural network predictions into the material robots are made of. Deep and shallow neural network models are first trained offline using state-of-the-art machine learning…
Advances in artificial intelligence (AI) and deep learning have raised concerns about its increasing energy consumption, while demand for deploying AI in mobile devices and machines at the edge is growing. Binary neural networks (BNNs) have…
In autonomous embedded systems, it is often vital to reduce the amount of actions taken in the real world and energy required to learn a policy. Training reinforcement learning agents from high dimensional image representations can be very…
Experimental particle physics demands a sophisticated trigger and acquisition system capable to efficiently retain the collisions of interest for further investigation. Heterogeneous computing with the employment of FPGA cards may emerge as…
Recent work has shown that fast, compact low-bitwidth neural networks can be surprisingly accurate. These networks use homogeneous binarization: all parameters in each layer or (more commonly) the whole model have the same low bitwidth…
Recent technological advances have proliferated the available computing power, memory, and speed of modern Central Processing Units (CPUs), Graphics Processing Units (GPUs), and Field Programmable Gate Arrays (FPGAs). Consequently, the…
Recognition of objects in still images has traditionally been regarded as a difficult computational problem. Although modern automated methods for visual object recognition have achieved steadily increasing recognition accuracy, even the…
Athletic robots demand a whole-body actuation system design that utilizes motors up to the boundaries of their performance. However, creating such robots poses challenges of integrating design principles and reasoning of practical design…
FPGA-based hardware accelerators for convolutional neural networks (CNNs) have obtained great attentions due to their higher energy efficiency than GPUs. However, it is challenging for FPGA-based solutions to achieve a higher throughput…
Binary neural networks (BNNs) have 1-bit weights and activations. Such networks are well suited for FPGAs, as their dominant computations are bitwise arithmetic and the memory requirement is also significantly reduced. However, compared to…
In recent years, deep learning has become more and more mature, and as a commonly used algorithm in deep learning, convolutional neural networks have been widely used in various visual tasks. In the past, research based on deep learning…
The bilateral filter (BF) is widely used in image processing because it can perform denoising while preserving edges. It has disadvantages in that it is nonlinear, and its computational complexity and hardware resources are directly…
Driveable area detection is a key component for various applications in the field of autonomous driving (AD), such as ground-plane detection, obstacle detection and maneuver planning. Additionally, bulky and over-parameterized networks can…
Machine learning-based embedded systems for safety-critical applications, such as aerospace and autonomous driving, must be robust to perturbations caused by soft errors. As transistor geometries shrink and voltages decrease, modern…
Autonomous control systems onboard planetary rovers and spacecraft benefit from having cognitive capabilities like learning so that they can adapt to unexpected situations in-situ. Q-learning is a form of reinforcement learning and it has…