Autonomous driving has advanced significantly due to sensors, machine learning, and artificial intelligence improvements. However, prevailing methods struggle with intricate scenarios and causal relationships, hindering adaptability and interpretability in varied environments. To address the above problems, we introduce LeapAD, a novel paradigm for autonomous driving inspired by the human cognitive process.

LeapAD, a novel paradigm for autonomous driving inspired by the human cognitive process.

Mobile robots are increasingly required to navigate and interact within unknown and unstructured environments to meet human demands. Demand-driven navigation (DDN) enables robots to identify and locate objects based on implicit human intent, even when object locations are unknown. However, traditional data-driven DDN methods rely on pre-collected data for model training and decision-making, limiting their generalization capability in unseen scenarios. In this paper, we propose CogDDN, a VLM-based framework that emulates the human cognitive and learning mechanisms by integrating fast and slow thinking systems and selectively identifying key objects essential to fulfilling user demands. CogDDN identifies appropriate target objects by semantically aligning detected objects with the given instructions. Furthermore, it incorporates a dual-process decision-making module, comprising a Heuristic Process for rapid, efficient decisions and an Analytic Process that analyzes past errors, accumulates them in a knowledge base, and continuously improves performance. Chain of Thought (CoT) reasoning strengthens the decision-making process. Extensive closed-loop evaluations on the AI2Thor simulator with the ProcThor dataset show that CogDDN outperforms single-view camera-only methods by 15\%, demonstrating significant improvements in navigation accuracy and adaptability. The project page is available at https://yuehaohuang.github.io/CogDDN/.

Autonomous driving has advanced significantly due to sensors, machine learning, and artificial intelligence improvements. However, prevailing methods struggle with intricate scenarios and causal relationships, hindering adaptability and interpretability in varied environments. To address the above problems, we introduce LeapAD, a novel paradigm for autonomous driving inspired by the human cognitive process. Additionally, LeapAD incorporates an innovative dual-process decision-making module, which consists of an Analytic Process (System-II) for thorough analysis and reasoning, along with a Heuristic Process (System-I) for swift and empirical processing. The Analytic Process leverages its logical reasoning to accumulate linguistic driving experience, which is then transferred to the Heuristic Process by supervised fine-tuning.

While autonomous driving technology has made remarkable strides, data-driven approaches still struggle with complex scenarios due to their limited reasoning capabilities. Meanwhile, knowledge-driven autonomous driving systems have evolved considerably with the popularization of visual language models. In this paper, we propose LeapVAD, a novel method based on cognitive perception and dual-process thinking. Our approach implements a human-attentional mechanism to identify and focus on critical traffic elements that influence driving decisions. By characterizing these objects through comprehensive attributes - including appearance, motion patterns, and associated risks - LeapVAD achieves more effective environmental representation and streamlines the decision-making process. Furthermore, LeapVAD incorporates an innovative dual-process decision-making module miming the human-driving learning process. The 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. LeapVAD also includes reflective mechanisms and a growing memory bank, enabling it to learn from past mistakes and continuously improve its performance in a closed-loop environment. To enhance efficiency, we develop a scene encoder network that generates compact scene representations for rapid retrieval of relevant driving experiences. Extensive evaluations conducted on two leading autonomous driving simulators, CARLA and DriveArena, demonstrate that LeapVAD achieves superior performance compared to camera-only approaches despite limited training data. Comprehensive ablation studies further emphasize its effectiveness in continuous learning and domain adaptation. Project page: https://pjlab-adg.github.io/LeapVAD/.

Autonomous driving has advanced significantly due to sensors, machine learning, and artificial intelligence improvements. However, prevailing methods struggle with intricate scenarios and causal relationships, hindering adaptability and interpretability in varied environments. To address the above problems, we introduce LeapAD, a novel paradigm for autonomous driving inspired by the human cognitive process. Specifically, LeapAD emulates human attention by selecting critical objects relevant to driving decisions, simplifying environmental interpretation, and mitigating decision-making complexities. Additionally, LeapAD incorporates an innovative dual-process decision-making module, which consists of an Analytic Process (System-II) for thorough analysis and reasoning, along with a Heuristic Process (System-I) for swift and empirical processing. The Analytic Process leverages its logical reasoning to accumulate linguistic driving experience, which is then transferred to the Heuristic Process by supervised fine-tuning. Through reflection mechanisms and a growing memory bank, LeapAD continuously improves itself from past mistakes in a closed-loop environment. Closed-loop testing in CARLA shows that LeapAD outperforms all methods relying solely on camera input, requiring 1-2 orders of magnitude less labeled data. Experiments also demonstrate that as the memory bank expands, the Heuristic Process with only 1.8B parameters can inherit the knowledge from a GPT-4 powered Analytic Process and achieve continuous performance improvement. Code will be released at https://github.com/PJLab-ADG/LeapAD.

Machine learning (ML) is one of the hottest and most lucrative tech trends. According to a survey on the state of AI conducted by McKinsey in 2021, 67 percent of companies that adopted AI-related technologies saw increases in revenue. Increased adoption of ML technology has given rise to some of the best machine learning startups, all of which are leading the digital transformation in the 21st Century. These machine learning startup companies are located around the globe, including San Francisco, Santa Clara, San Jose, San Mateo, Redwood City, and the rest of Silicon Valley, as well as places like London and Tel Aviv. This article will explore exciting startups in the private sector and public sector, looking at their innovative ideas, funding, and expected growth.

To address the concern for the ethical and societal implications of artificial intelligence systems, a possible solution is to have AI systems be audited for harm by investigators. We at the Frankfurt Big Data Lab at the Goethe University of Frankfurt, together with a team of international experts defined a novel holistic and analytic processes to assess Ethical AI, called Z-Inspection. Z-Inspection is a general inspection process for Ethical AI which can be applied to a variety of domains such as business, healthcare, public sector, etc. To the best of our knowledge, Z-Inspection is the first process that combines a holistic and analytic approach to assess Ethical AI in practice. Our assessment takes into account the "Framework for Trustworthy AI" and the seven key requirements that AI systems should meet in order to be deemed trustworthy, defined by the independent High-Level Expert Group of Artificial Intelligence [1], set by the European Commission, and also confirmed by a recent report of The Organization for Economic Co-operation and Development (OECD).

Data visualization tools, desktop data discovery tools, and visual analytics are examples of traditional self-service BI tools that business analysts embrace because they provide a user-friendly way of quickly turning data into insights. These tools are geared toward business analysts that have the skills and knowledge to acquire the right data sets, perform the analysis, and present the insights needed to solve a business problem. Often, these data sets acquired by business analysts are not governed or managed by IT, but this is acceptable because business analysts have enough business knowledge to evaluate whether insights are reasonably accurate to address the business problem. Business analysts also have the skills to best present analysis in the form of beautiful charts and reports to make it easy for others in the business to interpret insights quickly for decision making. Machine-generated insights can remove business analysts entirely from the analytic process.