A Multiplicative Value Function for Safe and Efficient Reinforcement Learning. IROS 2023.

The code for the articel "Reducing Safety Interventions in Provably Safe Reinforcement Learning".

Repository of the work: Improving robot navigation in crowded environments using intrinsic rewards (ICRA 2023)

[ICRA 2023] Intention Aware Robot Crowd Navigation with Attention-Based Interaction Graph

Occlusion-Aware Crowd Navigation Using People as Sensors: ICRA2023

[T-RO 2023] DRL-VO: Learning to Navigate Through Crowded Dynamic Scenes Using Velocity Obstacles

Learning to Identify Critical States for Reinforcement Learning from Videos (Accepted to ICCV'23)

Change-Based Exploration Transfer

iPlanner: Imperative Path Planning. An end-to-end learning planning framework using a novel unsupervised imperative learning approach

DRL-VO navigation policy for BARN Challenge

Repository for the paper on crowd prediction models and navigation: https://arxiv.org/abs/2303.01424