AI Agent Driven Sensing, Data Acquisition, and Signal Processing Methods in Autonomous Driving
A special issue of Sensors (ISSN 1424-8220). This special issue belongs to the section "Vehicular Sensing".
Deadline for manuscript submissions: 31 August 2026 | Viewed by 694
Special Issue Editors
Interests: motion planning; computational optimal control; robotics; autonomous driving; AI agent
Special Issues, Collections and Topics in MDPI journals
Interests: advanced driver assistance systems; human-vehicle interaction; human-in-the-loop; driving envelope; collision avoidance; safety assessment
Special Issue Information
Dear Colleagues,
In autonomous driving, system-level autonomy is increasingly being shaped not only by perception and control algorithms but also by agentic decision-making that can plan, decompose tasks, invoke tools/models, and supervise execution under changing conditions. In this Special Issue, “AI agent” refers to an autonomous software entity (or a coordinated set of entities) that pursues driving goals with a certain degree of autonomy by combining reasoning, planning, memory, tool use, and outcome validation, rather than a narrow “agent” in the reinforcement learning sense. This concept has been widely described as goal-driven systems that can independently decide actions and execute multi-step workflows via available tools and feedback loops. Against this backdrop, AI agent-driven autonomous driving technologies emphasize closed-loop and system-level intelligence: agents can orchestrate heterogeneous modules (e.g., perception, prediction, mapping, risk assessment, motion planning, and control), call external tools or specialized models for grounding and verification, and coordinate multiple agents (vehicle–vehicle, vehicle–infrastructure, or multi-modal agents) to handle negotiation, intention sharing, and complex interactive scenarios. Recent studies on LLM/VLM-based driving–agent frameworks further highlight the opportunity to connect high-level reasoning with 3D driving tasks and active perception, improving interpretability and robustness when deployed in realistic environments. This Special Issue aims to publish state-of-the-art research and review articles that advance the theory, architecture, algorithms, and experimental validation of AI agent-driven autonomous driving, with particular interest in approaches that deliver measurable gains in safety, real-time performance, reliability, and deployability on embedded vehicle platforms. We welcome contributions that bridge agent intelligence with optimization-based motion planning/control, safety assurance, and engineering systems integration for real-world driving.
We seek high-quality original research and review articles focusing on innovative solutions applicable to real-world autonomous driving scenarios. Potential topics include, but are not limited to, the following:
- AI agents for autonomous driving.
- Agent-driven decision making and system-level autonomy.
- Task decomposition and tool-augmented driving intelligence.
- LLM/VLM-enabled autonomous driving agents.
- Multi-agent coordination and interaction in traffic scenarios.
- Agent-supervised optimization-based motion planning and control.
- Risk-aware and safety-critical agentic decision making.
- Real-time agent-based planning, control, and execution monitoring.
- Embedded and compute-aware deployment of driving agents.
- Verification, validation, and safety assurance for AI agent–driven driving systems.
We look forward to receiving your contributions.
Prof. Dr. Bai Li
Dr. Xiaohui Li
Guest Editors
Manuscript Submission Information
Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 250 words) can be sent to the Editorial Office for assessment.
Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Sensors is an international peer-reviewed open access semimonthly journal published by MDPI.
Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.
Keywords
- AI agents
- agent-driven autonomy
- autonomous driving systems
- multi-agent coordination
- agent-based decision making
- agent-supervised control
- risk-aware driving
- real-time autonomy
- safety assurance
Benefits of Publishing in a Special Issue
- Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
- Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
- Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
- External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
- Reprint: MDPI Books provides the opportunity to republish successful Special Issues in book format, both online and in print.
Further information on MDPI's Special Issue policies can be found here.
