Search papers, labs, and topics across Lattice.
RoadWeaver introduces a novel coarse-to-fine framework for generating large-scale, lane-level HD maps from scratch, addressing the limitations of existing handcrafted or reconstructed mapping methods. By synthesizing a global road layout and constructing topologically consistent lane connectivity, RoadWeaver achieves impressive metrics, including 99.8% reachability and a 94.4% reduction in endpoint alignment error compared to state-of-the-art methods. This capability enables the rapid generation of complete HD maps in just 1.39 to 3.50 seconds, facilitating scalable simulation environments for autonomous driving evaluation.
Achieving 99.8% reachability and a 94.4% reduction in alignment error, RoadWeaver revolutionizes HD map generation for autonomous driving simulations.
Autonomous driving simulation requires diverse and scalable lane-level HD maps to support long-horizon evaluation across complex road networks. Existing approaches either rely on handcrafted or reconstructed real-world maps, which limits scalability, or generate only local road structures rather than complete HD maps. We present RoadWeaver, a coarse-to-fine framework for from-scratch generation of diverse, large-scale HD maps. RoadWeaver first synthesizes a global road layout, expands it into a connected road network, and then constructs lane-level geometry with topologically consistent lane connectivity. Experimental results show that RoadWeaver achieves a 99.8\% reachability, a 10.7\% dead-end ratio, and an endpoint alignment error of 0.24 m. Compared with SOTA generation methods, it reduces endpoint alignment error by 94.4\% while generating complete HD maps in 1.39--3.50 s. The generated maps can be directly deployed in driving simulators, providing scalable simulation environments for future closed-loop evaluation of autonomous driving systems. The training code and an out-of-the-box implementation of RoadWeaver will be released upon acceptance.
