Large Language models (LLMs) have garnered significant attention for their ability to understand text and images, generate human-like text, and perform complex reasoning tasks. However, their ability to generalize thi...
详细信息
ISBN:
(纸本)9798331517519;9798331517526
Large Language models (LLMs) have garnered significant attention for their ability to understand text and images, generate human-like text, and perform complex reasoning tasks. However, their ability to generalize this advanced reasoning with a combination of natural language text for decision-making in dynamic situations requires further exploration. In this study, we investigate how well LLMs can adapt and apply a combination of arithmetic and common-sense reasoning, particularly in autonomous driving scenarios. We hypothesize that LLMs' hybrid reasoning abilities can improve autonomous driving by enabling them to analyze detected object and sensor data, understand driving regulations and physical laws, and offer additional context. This addresses complex scenarios, like decisions in low visibility (due to weather conditions), where traditional methods might fall short. We evaluated LLM based on accuracy by comparing their answers with human-generated ground truth inside CARLA. The results showed that when a combination of images (detected objects) and sensor data is fed into the LLM, it can offer precise information for brake and throttle control in autonomous vehicles across various weather conditions. This formulation and answers can assist in decision-making for autopilot systems.
In this paper, a battery State of Charge (SOC) estimation method based on the extended Kalman filter is proposed. In some known battery SOC estimation methods, it is assumed that the relationship between battery open ...
详细信息
Model predictive control (MPC) has been widely used in a wide range of industrial fields. How to balance the accuracy and real-time of the MPC-based controllers is still a challenging problem. In terms of the controll...
详细信息
This paper proposes a calibration strategy for distorted camera with high-precision. It makes use of planar homogrphy constraint to estimate intrinsic and extrinsic parameter. On the basis of this initial guess, an op...
详细信息
ISBN:
(纸本)0780384636
This paper proposes a calibration strategy for distorted camera with high-precision. It makes use of planar homogrphy constraint to estimate intrinsic and extrinsic parameter. On the basis of this initial guess, an optimization scheme is used to minimize a new cost function, which is based on a Perspective 3-Point (P3P) algorithm. All the calibration parameters are globally optimized simultaneously with Genetic Algorithm(GA). Simulation and real image experiment result show this technique have much higher precision than traditional methods.
In this study, the dynamics and control aspects of a spherical rolling robot's lateral motion are investigated. An approximate, simplified to a single plane, mathematical model is derived using Lagrange equations ...
In this study, the dynamics and control aspects of a spherical rolling robot's lateral motion are investigated. An approximate, simplified to a single plane, mathematical model is derived using Lagrange equations to check stability of the system. Utilizing the fusion of sensor data, a precise orientation measurement is achieved. Document focuses on a synthesis of a PID controller reducing sideway oscillations that occur in motion of a spherical robot with internal pendulum mechanism.
The impact of the selected Lyapunov function on the performance of a nonlinear system designed by adaptive backstepping is considered. Special attention is paid to the comparison of various Barrier Lyapunov Functions,...
详细信息
The impact of the selected Lyapunov function on the performance of a nonlinear system designed by adaptive backstepping is considered. Special attention is paid to the comparison of various Barrier Lyapunov Functions, which assure preservation of hard state constraints during any transient. The differences in the system operation are discussed and some recommendations the Lyapunov function selection are given.
Nerve injury after stroke usually weakens the trunk muscle strength (TMS) and balance function, which increases the risk of falling and affects the Activities of Daily Living (ADL). Thus a novel fall prevention device...
详细信息
We present a novel approach to build approximate maps of structured environments utilizing human motion and activity. Our approach uses data recorded with a data suit which is equipped with several IMUs to detect move...
详细信息
A general tracking problem is formulated and solved for a third-order Duffing-Holmes type chaotic oscillator implemented as an electronic circuit with unknown parameters. Two nonlinear controllers, based on adaptive b...
详细信息
A general tracking problem is formulated and solved for a third-order Duffing-Holmes type chaotic oscillator implemented as an electronic circuit with unknown parameters. Two nonlinear controllers, based on adaptive backstepping techniques, are derived and compared. Both are sufficiently robust and accurate for practical implementation. The same approach may be used for chaos stabilization and synchronization.
In the present paper we present a control system of robotic shift in hybrid vehicles that utilizes fussy logic as well as optimization techniques (genetic algorithms) aimed at improving, with the automatic choice of t...
详细信息
ISBN:
(纸本)9780780394018
In the present paper we present a control system of robotic shift in hybrid vehicles that utilizes fussy logic as well as optimization techniques (genetic algorithms) aimed at improving, with the automatic choice of the shifting, the objective-functions previously chosen (minimum consumption, suitable dynamic performances). Following the working oat of a model in Simulink environment, which is suitable for the simulation of the behavior of a hybrid vehicle equipped with different shifts (manual, robotic, robotic fussy-logic) we carried out tests in a virtual lab and compared the results with those obtained with models previously built by others (CRF) that had been validated on real vehicles. The results of the simulations have shown, on the one hand, the validity of the robotic shift relative to the manual shift, and, on the other hand, the effectiveness of the application of soft-computing for the development of the robotic shift relative to a vehicle equipped with a traditional robotic shift, in which the logic of shifting is managed by static maps.
暂无评论