Bidirectional Planning for Autonomous Driving Framework with Large Language Model DOI Creative Commons
Z. Ma, Quanbin Sun, Takafumi Matsumaru

и другие.

Sensors, Год журнала: 2024, Номер 24(20), С. 6723 - 6723

Опубликована: Окт. 19, 2024

Autonomous navigation systems often struggle in dynamic, complex environments due to challenges safety, intent prediction, and strategic planning. Traditional methods are limited by rigid architectures inadequate safety mechanisms, reducing adaptability unpredictable scenarios. We propose SafeMod, a novel framework enhancing autonomous driving improving decision-making scenario management. SafeMod features bidirectional planning structure with two components: forward backward Forward predicts surrounding agents' behavior using text-based environment descriptions reasoning via large language models, generating action predictions. These embedded into transformer-based planner that integrates text image data produce feasible trajectories. Backward refines these trajectories policy value functions learned through Actor-Critic-based reinforcement learning, selecting optimal actions based on probability distributions. Experiments CARLA nuScenes benchmarks demonstrate outperforms recent both real-world simulation testing, significantly decision-making. This underscores SafeMod's potential effectively integrate considerations driving.

Язык: Английский

Artificial Intelligence (AI) Algorithm and Models for Embodied Agents (Robots and Drones) DOI

P. Chitra,

A. Saleem Raja

Опубликована: Янв. 1, 2024

Язык: Английский

Процитировано

1
Development of Transformative Leadership for Head of State Madrasah Aliyah DOI Open Access

N Dewi Hasanah,

Badrudin Badrudin,

Hary Priatna Sanusi

и другие.

AL-HAYAT Journal of Islamic Education, Год журнала: 2023, Номер 7(2), С. 626 - 626

Опубликована: Сен. 12, 2023

Leadership is an essential element in organizational speed. Mastery of leadership theory can make a significant contribution to the madrasah principal. This research aims examine influence transformative heads on teacher performance two madrasahs Bandung. uses qualitative approach. Collecting data with interview techniques, observation, and documentation. Informants this study involved head madrasah, deputy curriculum, teachers students. Data analysis techniques include reduction, presentation, conclusions, validity testing. The results show that principal strategy builds commitment through regular supervision monitoring. provides inspirational communication, motivates afterlife goals, instils discipline habits. In dealing criticism, open democratic involves all members policy-making. approach shows constructive honest intellectual stimulus. madrasa awards who excel offers advice need it. emphasizes importance improving quality realizing Madrasahs are akhlakul karimah.

Язык: Английский

Процитировано

1
Bidirectional Planning for Autonomous Driving Framework with Large Language Model DOI Creative Commons
Z. Ma, Quanbin Sun, Takafumi Matsumaru

и другие.

Sensors, Год журнала: 2024, Номер 24(20), С. 6723 - 6723

Опубликована: Окт. 19, 2024

Autonomous navigation systems often struggle in dynamic, complex environments due to challenges safety, intent prediction, and strategic planning. Traditional methods are limited by rigid architectures inadequate safety mechanisms, reducing adaptability unpredictable scenarios. We propose SafeMod, a novel framework enhancing autonomous driving improving decision-making scenario management. SafeMod features bidirectional planning structure with two components: forward backward Forward predicts surrounding agents' behavior using text-based environment descriptions reasoning via large language models, generating action predictions. These embedded into transformer-based planner that integrates text image data produce feasible trajectories. Backward refines these trajectories policy value functions learned through Actor-Critic-based reinforcement learning, selecting optimal actions based on probability distributions. Experiments CARLA nuScenes benchmarks demonstrate outperforms recent both real-world simulation testing, significantly decision-making. This underscores SafeMod's potential effectively integrate considerations driving.

Язык: Английский

Процитировано

0