Generative AI offers new opportunities for automating urban planning by creating site-specific urban layouts and enabling flexible design exploration. However, existing approaches often struggle to produce realistic and practical designs at scale. Therefore, we adapt a state-of-the-art Stable Diffusion model, extended with ControlNet, to generate high-fidelity satellite imagery conditioned on land use descriptions, infrastructure, and natural environments. To overcome data availability limitations, we spatially link satellite imagery with structured land use and constraint information from OpenStreetMap. Using data from three major U.S. cities, we demonstrate that the proposed diffusion model generates realistic and diverse urban landscapes by varying land-use configurations, road networks, and water bodies, facilitating cross-city learning and design diversity. We also systematically evaluate the impacts of varying language prompts and control imagery on the quality of satellite imagery generation. Our model achieves high FID and KID scores and demonstrates robustness across diverse urban contexts. Qualitative assessments from urban planners and the general public show that generated images align closely with design descriptions and constraints, and are often preferred over real images. This work establishes a benchmark for controlled urban imagery generation and highlights the potential of generative AI as a tool for enhancing planning workflows and public engagement.

In contemporary design practices, the integration of computer vision and generative artificial intelligence (genAI) represents a transformative shift towards more interactive and inclusive processes. These technologies offer new dimensions of image analysis and generation, which are particularly relevant in the context of urban landscape reconstruction. This paper presents a novel workflow encapsulated within a prototype application, designed to leverage the synergies between advanced image segmentation and diffusion models for a comprehensive approach to urban design. Our methodology encompasses the OneFormer model for detailed image segmentation and the Stable Diffusion XL (SDXL) diffusion model, implemented through ControlNet, for generating images from textual descriptions. Validation results indicated a high degree of performance by the prototype application, showcasing significant accuracy in both object detection and text-to-image generation. This was evidenced by superior Intersection over Union (IoU) and CLIP scores across iterative evaluations for various categories of urban landscape features. Preliminary testing included utilising UrbanGenAI as an educational tool enhancing the learning experience in design pedagogy, and as a participatory instrument facilitating community-driven urban planning. Early results suggested that UrbanGenAI not only advances the technical frontiers of urban landscape reconstruction but also provides significant pedagogical and participatory planning benefits. The ongoing development of UrbanGenAI aims to further validate its effectiveness across broader contexts and integrate additional features such as real-time feedback mechanisms and 3D modelling capabilities. Keywords: generative AI; panoptic image segmentation; diffusion models; urban landscape design; design pedagogy; co-design

Makram Chahine, a PhD student in electrical engineering and computer science and an MIT CSAIL affiliate, leads a drone used to test liquid neural networks. In the vast, expansive skies where birds once ruled supreme, a new crop of aviators is taking flight. These pioneers of the air are not living creatures, but rather a product of deliberate innovation: drones. Rather, they're avian-inspired marvels that soar through the sky, guided by liquid neural networks to navigate ever-changing and unseen environments with precision and ease. Inspired by the adaptable nature of organic brains, researchers from MIT's Computer Science and Artificial Intelligence Laboratory (CSAIL) have introduced a method for robust flight navigation agents to master vision-based fly-to-target tasks in intricate, unfamiliar environments.

Future commercial developments will include dedicated drop-off and pick-up zones for autonomous ride vehicles rather than on-site parking, according to design firm Gensler. A world in which robotic ride and delivery services are commonplace is years away, but what to do if you've got big-ticket commercial real estate projects in the works now? Turns out that future is already being baked in, according to the largest U.S. architecture firm. The full impact of self-driving vehicle technology will unfold over years, but Andy Cohen, the Los Angeles-based co-CEO for design firm Gensler, is convinced it will bring the end of parking structures as we know them, require more expansive building drop-off and pickup zones and more elaborate entry lobbies. Over time it opens up opportunities to reclaim curb space dedicated to metered parking and redevelop land in prime urban spots currently taken up by gas stations.

In our ongoing speculative design project entitled Topos, we propose a public-facing, tangible user interface (TUI) that makes legible and accessible the AI systems embedded in near-future urban landscapes. By imagining AI as a public service, Topos interrogates the creation of public trust between people and AI systems through the medium of physical structures in public space. We propose that urban landscapes will contain “AI-parks” containing trees of knowledge that physicalize machine learning (ML) pathways that take on or augment the responsibilities of city departments and bureaus. The trees of knowledge are TUIs where humans can read and revise the inputs that civic AI systems learn from—an interaction that we call “pruning”. Topos suggests that the interactions between AI systems and humans should be embodied and spatial in nature, so as to highlight the ways in which civic-oriented AI systems will directly affect the lived environments and multiple infrastructures of the urban landscape.

You might think putting a helipad on Trump Tower would give the president's Manhattan residence an added veneer of affluence. After all, nothing conveys wealth and power quite like arriving at your own skyscraper aboard Marine One, right? Not according to Penny, an artificial intelligence that uses satellite imagery to predict income levels in the Big Apple and how they change as you tinker with the urban landscape. When I called up the president's Manhattan residence via Penny's clean, intuitive interface, it saw nothing but wealth. "PENNY is 100% confident that this is a HIGH median income area," it reported.