UMD     This Site

The authors predict the long-term (3-5 seconds) trajectories of road-agents, as well as their behavior (e.g. overspeeding, braking, etc.), in urban traffic scenes.

The authors predict the long-term (3-5 seconds) trajectories of road-agents, as well as their behavior (e.g. overspeeding, braking, etc.), in urban traffic scenes.


New work by the Geometric Algorithms for Modeling, Motion and Animation (GAMMA) research team uses a combination of spectral graph analysis and deep learning for traffic forecasting in urban traffic scenarios. The research will be of use to future autonomous vehicles. The team includes Rohan Chandra, Tianrui Guan, Srujan Panuganti, Trisha Mittal, Uttaran Bhattacharya, Aniket Bera, and ISR-affiliated Professor Dinesh Manocha (CS/ECE/UMIACS).

In their paper, Forecasting Trajectory and Behavior of Road agents Using Spectral Clustering in Graph-LSTMs, the researchers predict both low-level information (future trajectories) as well as high-level information (road agent behavior) from the extracted trajectory of each road agent. The formulation represents the proximity between the road agents using a dynamic weighted traffic-graph.

A two-stream graph convolutional LSTM network is used to perform traffic forecasting using these weighted traffic-graphs. The first stream predicts the spatial coordinates of road agents, while the second stream predicts whether a road agent is going to exhibit aggressive, conservative, or normal behavior. The researchers introduce spectral cluster regularization to reduce error margin in long-term prediction (3-5 seconds) and improve the accuracy of predicted trajectories. They evaluated their approach on the Argoverse, Lyft, and Apolloscape datasets and highlighted the benefits over prior trajectory prediction methods.

In practice, the new approach reduces average prediction error by more than 54% over prior algorithms and achieves a weighted average accuracy of 91.2% for behavior prediction.

The method has some limitations. Only one feature was used to design the behavior prediction model, which may not be able to generalize to new traffic scenarios. In addition, training is slow and takes several hours due to the number of computations required for computing the traffic graphs and corresponding Laplacian matrices. As the research progresses, behavior prediction will become data-driven, rather than rule-based. In addition, implementation will be optimized using GPU parallelization to improve the runtime.

Related Articles:
RoadTrack algorithm could help autonomous vehicles navigate dense traffic scenarios
Who's walking deceptively? Manocha's team thinks they know.
Alumnus Zhenyu Lin is Google software development engineer
Alumnus Hyun Jung and colleagues claim top spot in MoNuSAC challenge
A cooperative control algorithm for robotic search and rescue
Workshop focuses on needs of autonomous agent networks
AlphaGo family of AI programs grew from AMS simulation-based algorithms developed at UMD
Add-on mechanism could increase safety for networked vehicles
Realistic simulator improves safety of self-driving vehicles before road testing
Do Good Robotics Symposium to explore technologies that benefit society and the planet

December 9, 2019

«Previous Story  



Current Headlines

Equipping Drones to Recover When Things Go Wrong

Srivastava testing security of new delay locking technology

AIAA journal paper describes new UAV hazard mitigation software module

Search Initiated for New Clark School Dean

'Perfect adherence' to COVID vaccine prioritization hampering distribution says Mike Ball

Ph.D. student Gustavo Varela-Alvarenga featured in ORISE profile

Paley receives ONR funding for cross-domain cooperative control

Deliberation Computation: The Data Behind Decision Making

The Mystery of Our Early Missing Memories

UMD Makes U.S. DOE Solar District Cup Finals

Back to top  
Home Clark School Home UMD Home