A leakage-aware protocol with vessel-, time- and region-disjoint splits is built and applied to two corpora with different traffic: 31 days of Danish national AIS traffic and 30 days of US Gulf coast traffic off Houston and Galveston.
Abstract
Reported gains in vessel-trajectory prediction from Automatic Identification System (AIS) data are credited to new architectures, but the evaluation protocol is rarely measured as a source of error reduction. We build a leakage-aware protocol with vessel-, time- and region-disjoint splits and apply it to two corpora with different traffic: 31 days of Danish national AIS traffic and 30 days of US Gulf coast traffic off Houston and Galveston. On both, we audit TrAISformer, GATransformer, and controlled AISFormer-inspired reconstructions. Three protocol effects appear in both corpora. First, TrAISformer's best-of-16 oracle decoder lowers error by a factor of 2.1-3.2 relative to greedy decoding. Second, a split that shares vessels lowers its greedy error by 23-25% at one hour, against 2% or less for a compact 0.43 M-parameter encoder. Third, a region-disjoint split raises TrAISformer's one-hour error from 2.2 to 24.6 km on the US corpus, because 99.9% of the test contexts fall in longitude bins never seen in training; the encoder built on local offsets is unaffected by this. Architectural mechanisms matter less: GATransformer's graph attention gives no measurable benefit on either corpus, while its waterway feature is worth 12-22%. The effect of a time-disjoint split is not stable across corpora (13% versus 2%). We release the splits and code.
It is suggested that multi-scale local motion modelling can stably improve the accuracy of AIS-based vessel trajectory prediction and is evaluated under a unified data preprocessing, resampling and multi-step autoregressive prediction framework.
Qi Xu, Hua-Sheng Nong, Tian-Wei Ma et al.· International Conference on...· 0 citations
We present BLInD (Blind Learned Intent Distribution), a compact network that maps recent vehicle-state history (e.g. speed, curvature, indicator, and vehicle type) to a top-k distribution of future ego trajectories, with no camera, LiDAR, map, or object-track inputs. We find that vehiclestate history alone is sufficien...
Flavian Pegado, Ronit Hire, Shreyas Rajesh et al.· 0 citations
Covert navigation in an uncertain flow couples motion planning with information acquisition. A vehicle must estimate the local flow to navigate, while estimation error induces corrective maneuvers that increase statistical distinguishability, or leakage, and hence the vehicle's detectability. We model this coupling by...
Experimental results demonstrate that TempTPI consistently outperforms existing methods across prediction windows of 1 to 5 hours, and achieves a 55% improvement in Mean Squared Error (MSE) at a 5-hour horizon, offering a robust solution for long-range maritime situational awareness.
Kevin Ferneding, Veronika Lietavcova, Aleksandra M. Blachowiak et al.· 0 citations
Reliable mobility analytics require compact trajectory representations and evaluation procedures that limit information leakage and overly optimistic conclusions. This study evaluates unsupervised autoencoder-based trajectory representations across maritime Automatic Identification System (AIS) and human-mobility Globa...
Accurate medium-horizon trajectory prediction, spanning roughly one to three seconds ahead, is essential for the safety and autonomy of uncrewed aerial vehicle (UAV) systems. Trajectory prediction assists UAVs in performing collision avoidance, path planning, and cooperative airspace coordination. Deep sequence models...
Shokoufeh Mirzaei, Sam Ly, Siddharth Raj et al.· Drones· 0 citations
Related blog posts
Microsoft Research Blog· microsoft.comNov 16, 2026
AI coding agents are increasingly help developers fix bugs and build features largely on their own, but every interaction with their models consumes tokens. In each session, an agent sends instructions, tool descriptions, and session history to its model. Most efforts to reduce this cost focus on individual tasks. Yet developers return to the same […] The post TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient appeared first on Microsoft Research.
MIT News · Artificial Intelligence· news.mit.eduNov 13, 2026