FASIONAD : FAst and Slow FusION Thinking Systems for Human-Like Autonomous Driving with Adaptive Feedback

• URL: http://arxiv.org/abs/2411.18013v1
• Date: Wed, 27 Nov 2024 03:14:16 GMT
• Title: FASIONAD : FAst and Slow FusION Thinking Systems for Human-Like Autonomous Driving with Adaptive Feedback
• Authors: Kangan Qian, Zhikun Ma, Yangfan He, Ziang Luo, Tianyu Shi, Tianze Zhu, Jiayin Li, Jianhui Wang, Ziyu Chen, Xiao He, Yining Shi, Zheng Fu, Xinyu Jiao, Kun Jiang, Diange Yang, Takafumi Matsumaru,
• Abstract summary: This paper presents FASIONAD, a novel dual-system framework inspired by the cognitive model "Thinking, Fast and Slow" The fast system handles routine navigation tasks using rapid, data-driven path planning, while the slow system focuses on complex reasoning and decision-making in challenging or unfamiliar situations. Visual prompts generated by the fast system enable human-like reasoning in the slow system, which provides high-quality feedback to enhance the fast system's decision-making.
• Score: 15.805379735361862
• License:
• Abstract: Ensuring safe, comfortable, and efficient navigation is a critical goal for autonomous driving systems. While end-to-end models trained on large-scale datasets excel in common driving scenarios, they often struggle with rare, long-tail events. Recent progress in large language models (LLMs) has introduced enhanced reasoning capabilities, but their computational demands pose challenges for real-time decision-making and precise planning. This paper presents FASIONAD, a novel dual-system framework inspired by the cognitive model "Thinking, Fast and Slow." The fast system handles routine navigation tasks using rapid, data-driven path planning, while the slow system focuses on complex reasoning and decision-making in challenging or unfamiliar situations. A dynamic switching mechanism based on score distribution and feedback allows seamless transitions between the two systems. Visual prompts generated by the fast system enable human-like reasoning in the slow system, which provides high-quality feedback to enhance the fast system's decision-making. To evaluate FASIONAD, we introduce a new benchmark derived from the nuScenes dataset, specifically designed to differentiate fast and slow scenarios. FASIONAD achieves state-of-the-art performance on this benchmark, establishing a new standard for frameworks integrating fast and slow cognitive processes in autonomous driving. This approach paves the way for more adaptive, human-like autonomous driving systems.

Related papers

• LeapVAD: A Leap in Autonomous Driving via Cognitive Perception and Dual-Process Thinking [13.898774643126174]
  LeapVAD implements a human-attentional mechanism to identify and focus on critical traffic elements that influence driving decisions. System consists of an Analytic Process (System-II) that accumulates driving experience through logical reasoning and a Heuristic Process (System-I) that refines this knowledge via fine-tuning and few-shot learning.
  arXiv  Detail & Related papers  (2025-01-14T14:49:45Z)
• Towards Selection and Transition Between Behavior-Based Neural Networks for Automated Driving [0.11470070927586014]
  This paper presents a new solution a Behavior Selector that uses multiple smaller artificial neural networks (ANNs) to manage different driving tasks. Rather than relying on a single large network, which can be burdensome, require extensive training data, and is hard to understand. We focus on ensuring smooth transitions between behaviors while considering the vehicles current speed and orientation to improve stability and safety.
  arXiv  Detail & Related papers  (2024-12-21T20:23:05Z)
• DiFSD: Ego-Centric Fully Sparse Paradigm with Uncertainty Denoising and Iterative Refinement for Efficient End-to-End Self-Driving [55.53171248839489]
  We propose an ego-centric fully sparse paradigm, named DiFSD, for end-to-end self-driving. Specifically, DiFSD mainly consists of sparse perception, hierarchical interaction and iterative motion planner. Experiments conducted on nuScenes and Bench2Drive datasets demonstrate the superior planning performance and great efficiency of DiFSD.
  arXiv  Detail & Related papers  (2024-09-15T15:55:24Z)
• Visual Agents as Fast and Slow Thinkers [88.1404921693082]
  We introduce FaST, which incorporates the Fast and Slow Thinking mechanism into visual agents. FaST employs a switch adapter to dynamically select between System 1/2 modes. It tackles uncertain and unseen objects by adjusting model confidence and integrating new contextual data.
  arXiv  Detail & Related papers  (2024-08-16T17:44:02Z)
• Brain-Inspired Visual Odometry: Balancing Speed and Interpretability through a System of Systems Approach [0.0]
  This study addresses the challenge of balancing speed and accuracy in visual odometry (VO) systems. Traditional VO systems often face a trade-off between computational speed and the precision of pose estimation. Our system is unique in its approach to handle each degree of freedom independently within the fully connected network (FCN)
  arXiv  Detail & Related papers  (2023-12-20T16:23:48Z)
• NeuroFlow: Development of lightweight and efficient model integration scheduling strategy for autonomous driving system [0.0]
  This paper proposes a specialized autonomous driving system that takes into account the unique constraints and characteristics of automotive systems. The proposed system systematically analyzes the intricate data flow in autonomous driving and provides functionality to dynamically adjust various factors that influence deep learning models.
  arXiv  Detail & Related papers  (2023-12-15T07:51:20Z)
• Interactive Autonomous Navigation with Internal State Inference and Interactivity Estimation [58.21683603243387]
  We propose three auxiliary tasks with relational-temporal reasoning and integrate them into the standard Deep Learning framework. These auxiliary tasks provide additional supervision signals to infer the behavior patterns other interactive agents. Our approach achieves robust and state-of-the-art performance in terms of standard evaluation metrics.
  arXiv  Detail & Related papers  (2023-11-27T18:57:42Z)
• FastRLAP: A System for Learning High-Speed Driving via Deep RL and Autonomous Practicing [71.76084256567599]
  We present a system that enables an autonomous small-scale RC car to drive aggressively from visual observations using reinforcement learning (RL) Our system, FastRLAP (faster lap), trains autonomously in the real world, without human interventions, and without requiring any simulation or expert demonstrations. The resulting policies exhibit emergent aggressive driving skills, such as timing braking and acceleration around turns and avoiding areas which impede the robot's motion, approaching the performance of a human driver using a similar first-person interface over the course of training.
  arXiv  Detail & Related papers  (2023-04-19T17:33:47Z)
• Scalable Vehicle Re-Identification via Self-Supervision [66.2562538902156]
  Vehicle Re-Identification is one of the key elements in city-scale vehicle analytics systems. Many state-of-the-art solutions for vehicle re-id mostly focus on improving the accuracy on existing re-id benchmarks and often ignore computational complexity. We propose a simple yet effective hybrid solution empowered by self-supervised training which only uses a single network during inference time.
  arXiv  Detail & Related papers  (2022-05-16T12:14:42Z)
• Combining Fast and Slow Thinking for Human-like and Efficient Navigation in Constrained Environments [43.178630971993286]
  Current AI systems lack several important human capabilities, such as adaptability, generalizability, self-control, consistency, common sense, and causal reasoning. We believe that existing cognitive theories of human decision making, such as the thinking fast and slow theory, can provide insights on how to advance AI systems towards some of these capabilities.
  arXiv  Detail & Related papers  (2022-01-18T15:24:03Z)
• Bayesian Optimization and Deep Learning forsteering wheel angle prediction [58.720142291102135]
  This work aims to obtain an accurate model for the prediction of the steering angle in an automated driving system. BO was able to identify, within a limited number of trials, a model -- namely BOST-LSTM -- which resulted, the most accurate when compared to classical end-to-end driving models.
  arXiv  Detail & Related papers  (2021-10-22T15:25:14Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.