A Contextual Bandit Approach for Learning to Plan in Environments with Probabilistic Goal Configurations

  title={A Contextual Bandit Approach for Learning to Plan in Environments with Probabilistic Goal Configurations},
  author={Sohan Rudra and Saksham Goel and Anirban Santara and Claudio Gentile and Laurent Perron and Fei Xia and Vikas Sindhwani and Carolina Parada and Gaurav Aggarwal},
Object-goal navigation (Object-nav) entails searching, recognizing and navigating to a target object. Object-nav has been extensively studied by the Embodied-AI community, but most solutions are often restricted to considering static objects (e.g., television, fridge, etc.). We propose a modular framework for object-nav that is able to efficiently search indoor environments for not just static objects but also movable objects (e.g. fruits, glasses, phones, etc.) that frequently change their… 



Object Goal Navigation using Goal-Oriented Semantic Exploration

A modular system called, `Goal-Oriented Semantic Exploration' which builds an episodic semantic map and uses it to explore the environment efficiently based on the goal object category and outperforms a wide range of baselines including end-to-end learning-based methods as well as modular map- based methods.

PONI: Potential Functions for ObjectGoal Navigation with Interaction-free Learning

A network that predicts two complementary potential functions conditioned on a semantic map and uses them to decide where to look for an unseen object is proposed, a modular approach that disentangles the skills of 'where to look?' for an object and 'how to navigate to $(x,\ y)$?’.

Learning Object-conditioned Exploration using Distributed Soft Actor Critic

This work presents a highly scalable implementation of an off-policy Reinforcement Learning algorithm, distributed Soft Actor Critic, which allows the system to utilize 98M experience steps in 24 hours on 8 GPUs, and learns to control a differential drive mobile base in simulation from a stack of high dimensional observations commonly used on robotic platforms.

Learning to Map for Active Semantic Goal Navigation

This work proposes a novel framework that actively learns to generate semantic maps outside the field of view of the agent and leverages the uncertainty over the semantic classes in the unobserved areas to decide on long term goals.

ObjectNav Revisited: On Evaluation of Embodied Agents Navigating to Objects

This document summarizes the consensus recommendations of this working group on ObjectNav and makes recommendations on subtle but important details of evaluation criteria, the agent's embodiment parameters, and the characteristics of the environments within which the task is carried out.

Learning to Explore using Active Neural SLAM

This work presents a modular and hierarchical approach to learn policies for exploring 3D environments, called `Active Neural SLAM'. Our approach leverages the strengths of both classical and

Learning Model Predictive Controllers with Real-Time Attention for Real-World Navigation

A new class of implicit control policies combining the benefits of imitation learning with the robust handling of system constraints from Model Predictive Control (MPC) are presented, called Performer-MPC, which achieves 40% better goal reached in cluttered environments and 65% better on social metrics when navigating around humans.

Scene Memory Transformer for Embodied Agents in Long-Horizon Tasks

A novel memory-based policy, named Scene Memory Transformer (SMT), which embeds and adds each observation to a memory and uses the attention mechanism to exploit spatio-temporal dependencies.

Neural Topological SLAM for Visual Navigation

This paper designs topological representations for space that effectively leverage semantics and afford approximate geometric reasoning, and describes supervised learning-based algorithms that can build, maintain and use such representations under noisy actuation.

Gibson Env: Real-World Perception for Embodied Agents

This paper investigates developing real-world perception for active agents, proposes Gibson Environment for this purpose, and showcases a set of perceptual tasks learned therein.