Rudra P.K. Poudel — accepted AI-conference papers

2024

ReCoRe: Regularized Contrastive Representation Learning of World Model

Rudra P.K. Poudel, Harit Pandya, Stephan Liwicki, Roberto Cipolla

CVPR 2024poster

While recent model-free Reinforcement Learning (RL) methods have demonstrated human-level effectiveness in gaming environments their success in everyday tasks like visual navigation has been limited particularly under significant appearance variations. This limitation arises from (i) poor sample eff…

Cited by 10 Source ↗PDF ↗Scholar ↗

2022

CoMBiNED: Multi-Constrained Model Based Planning for Navigation in Dynamic Environments

Harit Pandya, Rudra P.K. Poudel, Stephan Liwicki

IROS 2022poster

Recent deep reinforcement learning (DRL) approaches have achieved high success rate in map-less dynamic obstacle avoidance tasks. However, navigation in unseen dynamic scenarios without a pre-built map in the presence of dynamic obstacles still remains an open challenge. Since, learning accurate mod…

Cited by 0 Source ↗Scholar ↗