S2Planner is presented, a trajectory planner that combines three front-facing cameras with ego-motion history and the current driving command, and a coarse-to-fine decoder then uses trajectory self-attention and camera-projected cross-attention to refine candidate waypoints.
Abstract
We present S2Planner, a trajectory planner that combines three front-facing cameras with ego-motion history and the current driving command. A fine-tuned DINOv3 backbone and a Spatial Tuning Adapter produce multi-scale image features; a coarse-to-fine decoder then uses trajectory self-attention and camera-projected cross-attention to refine candidate waypoints. The contribution is the integration of ego-conditioned trajectory initialization with iterative, geometry-guided sampling of multi-scale image features, rather than a new visual backbone or attention operator. On the NAVSIM v1 non-reactive evaluation, the previously reported navtest run obtained 88.03 PDMS. Because that run was selected using navtest performance, this number is exploratory and cannot be interpreted as an unbiased test estimate. Validation-selected evaluation on unexposed data, repeated runs, and computational measurements are needed to establish generalization and efficiency.
This report adopts a two-piece MINCO parameterization, trading time for smoothness without altering the trajectory's spatial profile, and replaces score regression with a ranking loss, preventing small score errors from reordering the candidate set.
PAVER, Planning-Aligned BEV Encoder Pretraining is introduced, where from a single LiDAR sweep, PAVER constructs sparse risk and unknown targets describing occupied and unobserved evidence along rule-based ego motions, preserving the downstream architecture and camera-only inference.
This work proposes FeasibleFlow, a one-step end-to-end generative framework that jointly transports a configuration-space feasibility field and multimodal ego trajectories and introduces the Anchor-relative ranker (ARR) and Pareto-ReinFlow to balance safety and progress in candidate selection and generation.
iDriveVLA is proposed, a multi-modal planning framework that improves the candidate trajectory space while enabling more reliable and context-aware trajectory evaluation and develops an oracle-aligned progressive training strategy consisting of candidate imitation pretraining, candidate space refinement, and semantic r...
Ze-Yu He, Shi-Qi Liu, Ke Chen et al.· arXiv.org· 0 citations
This work introduces WAVE (Work-zone-focused AV data generation in Virtual and rEal Environments), a semi-automated pipeline for creating the dataset, and BoundaryFormer (BF), a transformer-based model that jointly predicts lane and work zone boundary polynomials and driving trajectories.
Nishad Sahu, Chang-Zhong Qian, Guang-Zhou Cai et al.· arXiv.org· 0 citations
EgoPathBench, a dataset and five-task benchmark for first-person waypoint decision-making, and Fine-tuning Qwen 3.5 4B on the released training split improves all four reported evaluations across three external spatial benchmarks, with gains of 1.4--9.6 points.
Known for his clear and elegant writing style, Bertsekas shaped fields from control and optimization to large-scale computation and artificial intelligence.