As residents attach more and more importance to healthy diet, the catering problem has garnered widespread public attention. Nutrient-based dietary planning can give viable dietary recommendations for the above proble...
详细信息
The financial sector is experiencing a transformation as a result of the incorporation of AI and robotics into banking operations, which has improved accuracy, efficiency, and client satisfaction. The utilization of r...
详细信息
Mixed integer convex and nonlinear programs, MICP and MINLP, are expressive but require long solving times. Recent work that combines learning methods on solver heuristics has shown potential to overcome this issue al...
详细信息
ISBN:
(纸本)9781728196817
Mixed integer convex and nonlinear programs, MICP and MINLP, are expressive but require long solving times. Recent work that combines learning methods on solver heuristics has shown potential to overcome this issue allowing for applications on larger scale practical problems. Gathering sufficient training data to employ these methods still present a challenge since getting data from traditional solvers are slow and newer learning approaches still require large amounts of data. In order to scale up and make these hybrid learning approaches more manageable we propose ReDUCE, a method that exploits structure within small to medium size datasets. We also introduce the bookshelf organization problem as an MINLP as a way to measure performance of solvers with ReDUCE. Results show that existing algorithms with ReDUCE can solve this problem within a few seconds, a significant improvement over the original formulation. ReDUCE is demonstrated as a high level planner for a robotic arm for the bookshelf problem.
Motion intention recognition has been widely used in fields such as robotics and medical assistance. However, traditional non-electromyographic signal cannot meet the demands of certain special scenarios, which limits...
详细信息
The integration of multiple pre-trained models in robotic navigation has the advantage of combining diverse strengths, leading to robust and generalized performance. However, the effectiveness of these models is often...
详细信息
ISBN:
(纸本)9789819607884;9789819607891
The integration of multiple pre-trained models in robotic navigation has the advantage of combining diverse strengths, leading to robust and generalized performance. However, the effectiveness of these models is often limited by path planning strategies, necessitating improvements in navigation capabilities. To overcome this, we introduce the Free-form Instruction Guided Robotic Navigation Path Planning with Large Vision-Language Model (FIG-RN). This model leverages free-form instructions to extract landmarks and directional cues, utilizing a pre-trained visual-language model to associate these landmarks with map nodes, thereby laying the groundwork for subsequent path planning. It evaluates landmark-node matches, node accessibility, and orientation to optimize path planning. Compared to traditional models, FIG-RN offers significant benefits: (i) it requires no map annotations due to its use of high-quality pre-trained models, (ii) it maximizes information use from instructions for better path efficacy, and (iii) it refines visual-language model matching values for improved local navigation. Experimentally, FIG-RN outperforms LM-Nav in success rate, efficiency, and accuracy, with improvements of 0.2, 0.2143, and 0.208, respectively.
Thematic is in the mechatronics and automation branches, appliccable in the robotics. The article analyses: the output mechanical energy of direct-current motor at motion, as well as how it corresponds to the mechanic...
详细信息
In this paper, we propose a formation control system for deforming and transporting simultaneously a deformable object with a team of robots, modeled with doubleintegrator dynamics. The goal is to reach a target confi...
详细信息
ISBN:
(纸本)9781728196817
In this paper, we propose a formation control system for deforming and transporting simultaneously a deformable object with a team of robots, modeled with doubleintegrator dynamics. The goal is to reach a target configuration, defined as a combination of shape, scale, orientation and position of the formation. We augment this controller with a set of control barrier functions (CBFs). The CBFs allow us to satisfy fundamental constraints for the success of the task: avoidance of agent-to-agent, agent-to-obstacle and objectto-obstacle collisions, and of excessive stretching. We test the performance of our proposal in different simulation scenarios.
We propose a novel framework to estimate the confidence of a disparity map taking into account, for the first time, the uncertainty affecting the confidence estimation process itself. Conversely to other tasks such as...
详细信息
ISBN:
(纸本)9781728196817
We propose a novel framework to estimate the confidence of a disparity map taking into account, for the first time, the uncertainty affecting the confidence estimation process itself. Conversely to other tasks such as disparity estimation, the uncertainty of confidence directly hints that the confidence should be increased if initially low, but with high uncertainty, decreased otherwise. By modelling such a cue in the form of a second-level confidence, or meta-confidence, our solution allows for finding incorrect predictions inferred by confidence estimator and for learning a correction for them. Our strategy is suited for any state-of-the-art method known in literature, either implemented using random forest classifiers or deep neural networks. Especially, for deep neural networksbased models, we present a multi-headed confidence estimator followed by an uncertainty network, so as to predict mean confidence and meta-confidence within a single network without the cost of lower accuracy, a known limitation in literature for uncertainty estimation. Experimental results on a variety of stereo algorithms and confidence estimation models prove that the modeled meta-confidence is meaningful of the reliability of the estimated confidence and allows for refining it.
We develop a task-independent predictive framework that estimates hip, knee and ankle future behavior from sonomyographic sensing of quadriceps musculature. Two regression models, support vector regression and Gaussia...
详细信息
ISBN:
(纸本)9781728196817
We develop a task-independent predictive framework that estimates hip, knee and ankle future behavior from sonomyographic sensing of quadriceps musculature. Two regression models, support vector regression and Gaussian process regression, were trained and tested such that no ambulation mode recognition was required. Sonomyography features of the anterior thigh musculature were extracted during the swing phase of level, incline and stair ambulation tasks as inputs to the two models for continuous prediction of the future stance phase hip, knee and ankle moments. Next, sonomyography features of the anterior thigh musculature were extracted during the stance phase and used to predict the following swing phase hip, knee and ankle angles. Leave-one-stride-out cross-validation is used to evaluate this continuous prediction framework. Additionally, initial, peak and terminal joint moment and angle parameters are extracted from trajectories and evaluated. Both regression models were able to accurately predict continuous future joint moments and angles, as well as initial, peak and terminal value parameters of future joint moments and angles. However, the support vector regression model required relatively lower computational cost. Thus, we recommend the support vector regression model as an optimal model for forward prediction of joint mechanics from sonomyographic sensing during ambulation.
In this paper, we propose a novel variable rate deep compression architecture that operates on raw 3D point cloud data. The majority of learning-based point cloud compression methods work on a downsampled representati...
详细信息
ISBN:
(纸本)9781728196817
In this paper, we propose a novel variable rate deep compression architecture that operates on raw 3D point cloud data. The majority of learning-based point cloud compression methods work on a downsampled representation of the data. Moreover, many existing techniques require training multiple networks for different compression rates to generate consolidated point clouds of varying quality. In contrast, our network is capable of explicitly processing point clouds and generating a compressed description at a comprehensive range of bitrates. Furthermore, our approach ensures that there is no loss of information as a result of the voxelization process and the density of the point cloud does not affect the encoder/decoder performance. An extensive experimental evaluation shows that our model obtains state-of-the-art results, it is computationally efficient, and it can work directly with point cloud data thus avoiding an expensive voxelized representation.
暂无评论