SOTAVerified

Trajectory Prediction

Trajectory Prediction is the problem of predicting the short-term (1-3 seconds) and long-term (3-5 seconds) spatial coordinates of various road-agents such as cars, buses, pedestrians, rickshaws, and animals, etc. These road-agents have different dynamic behaviors that may correspond to aggressive or conservative driving styles.

Source: Forecasting Trajectory and Behavior of Road-Agents Using Spectral Clustering in Graph-LSTMs

Papers

Showing 1–10 of 1004 papers

TitleStatusHype
Multi-Strategy Improved Snake Optimizer Accelerated CNN-LSTM-Attention-Adaboost for Trajectory Prediction—0
ILNet: Trajectory Prediction with Inverse Learning Attention for Enhancing Intention CaptureCode0
GoIRL: Graph-Oriented Inverse Reinforcement Learning for Multimodal Trajectory Prediction—0
AnchorDP3: 3D Affordance Guided Sparse Diffusion Policy for Robotic Manipulation—0
FlightKooba: A Fast Interpretable FTP Model—0
SceneAware: Scene-Constrained Pedestrian Trajectory Prediction with LLM-Guided WalkabilityCode0
Recent Advances in Multi-Agent Human Trajectory Prediction: A Comprehensive Review—0
IntTrajSim: Trajectory Prediction for Simulating Multi-Vehicle driving at Signalized Intersections—0
TrajFlow: Multi-modal Motion Prediction via Flow Matching—0
Egocentric Event-Based Vision for Ping Pong Ball Trajectory PredictionCode1
Show:102550
← PrevPage 1 of 101Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Bayesian-LSTMMSE(0.5)159—Unverified
2FOL-XMSE(0.5)147—Unverified
3PIE_trajMSE(0.5)110—Unverified
4BiTrap-DMSE(0.5)93—Unverified
5SGNetMSE(0.5)82—Unverified