REVIEW 5 cited by
Trajectron++: Dynamically-Feasible Trajectory Forecasting With Heterogeneous Data
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Reasoning about human motion is an important prerequisite to safe and socially-aware robotic navigation. As a result, multi-agent behavior prediction has become a core component of modern human-robot interactive systems, such as self-driving cars. While there exist many methods for trajectory forecasting, most do not enforce dynamic constraints and do not account for environmental information (e.g., maps). Towards this end, we present Trajectron++, a modular, graph-structured recurrent model that forecasts the trajectories of a general number of diverse agents while incorporating agent dynamics and heterogeneous data (e.g., semantic maps). Trajectron++ is designed to be tightly integrated with robotic planning and control frameworks; for example, it can produce predictions that are optionally conditioned on ego-agent motion plans. We demonstrate its performance on several challenging real-world trajectory forecasting datasets, outperforming a wide array of state-of-the-art deterministic and generative methods.
Forward citations
Cited by 5 Pith papers
-
Evaluating Generative Vehicle Trajectory Models for Traffic Intersection Dynamics
Trajectory prediction models that pass standard accuracy metrics still generate red-light violations, illegal stops, and near-collisions when evaluated online in a microsimulator, and new intersection-specific metrics...
-
IntTrajSim: Trajectory Prediction for Simulating Multi-Vehicle driving at Signalized Intersections
A CVAE with multi-head attention and traffic-signal encoding can be unrolled in a closed loop to simulate intersection traffic, with new safety-focused evaluation metrics; the model improves on some metrics but worsen...
-
STFlow: Data-Coupled Flow Matching for Geometric Trajectory Simulation
A flow-matching model that builds its starting noise from random walks matched to the observed motion produces more accurate trajectory predictions with only 5 integration steps.
-
Leaner Transformers: More Heads, Less Depth
The authors claim that more attention heads improve transformer conditioning enough to replace depth with width, yielding 30-50% parameter reductions at matched accuracy.
-
Causal Sensitivity Identification using Generative Learning
A CVAE-based framework claims to identify causal features through intervention and counterfactual perturbation, tested on Asia and GeoLife next-location prediction.
Discussion (0). Continue with ORCID to comment.