Abstract

Machine Learning Engineering is an evolving field that supports the exploration of different strategies in the design of reliable intelligent software. One such exploration involves, Transfer Learning which has become one of the standard methods to solve problems to overcome the isolated learning paradigm by utilizing knowledge acquired for one task to solve another related one. However, research needs to be done, to identify the initial steps before inducing transfer learning to applications for further verification and explainablity. In this research, we have performed cross dataset analysis and network architecture repair for the lane detection application in autonomous vehicles. Lane detection is an important aspect of autonomous vehicles’ driving assistance system. In most circumstances, modern deep-learning-based lane recognition systems are successful, but they struggle with lanes with complex topologies. The proposed architecture, ERF-CondLaneNet is an enhancement to the CondlaneNet used for lane identification framework to solve the difficulty of detecting lane lines with complex topologies like dense, curved and fork lines. The newly proposed technique was tested on two common lane detecting benchmarks, CULane and CurveLanes respectively, and two different backbones, ResNet and ERFNet. The researched technique with ERF-CondLaneNet, exhibited similar performance in comparison to Resnet-CondLaneNet, while using 33% less features, resulting in a reduction of model size by 46%.

About the Speaker

Siddhartha (Sid) Bhattacharyya's primary area of research expertise/interest is in machine learning engineering, model-based engineering, architectural analysis with formal methods for the design, verification and validation of intelligent autonomous systems, cyber security, and avionics. His research lab ASSIST (Assured Safety, Security, and Intent with Systematic Tactics) focuses on the design/development and application of innovative formal methods to assure the performance of intelligent systems, formally verify correctness or predict future behavior as it evolves and explore approaches in machine learning engineering for the development of reliable intelligent software. These research efforts have been funded through NASA, ONR, National Renewable Energy Labs (NREL), DARPA and other research agencies.