Inference

Related papers: 20

About

Inference, in the context of robotics and AI, refers to the process of drawing conclusions, making predictions, or deriving new knowledge from existing data, models, or learned representations. It encompasses both logical reasoning—deducing outcomes from rules or facts—and probabilistic reasoning, where uncertainty is explicitly modeled using frameworks such as Bayesian networks or probabilistic graphical models. In robotics and AI systems, inference occurs across a wide range of tasks: a robot localizing itself from sensor data, a neural network classifying objects in a scene, or a language model interpreting natural language commands. During deployment, inference typically means running a trained model on new inputs to produce outputs, as opposed to the training phase where parameters are learned. It also appears in planning and SLAM pipelines, where probabilistic inference resolves ambiguities in noisy, real-world measurements. Inference matters because it is the operational core of intelligent behavior—the mechanism by which systems translate raw data into actionable decisions. Efficient and accurate inference determines whether AI-powered robots can perceive, reason, and act reliably in dynamic, real-world environments, making it foundational to the entire field.

Top Cited Papers

Artificial intelligence: a modern approach

Citations: 22245 • 1995

Probabilistic graphical models : principles and techniques

Daniel L. Koller, Nir Friedman

Citations: 6456 • 2009

SECOND: Sparsely Embedded Convolutional Detection

Yan Yan, Yuxing Mao, Bo Li

Citations: 3212 • 2018

The Oxford Handbook of 4E Cognition

Citations: 1326 • 2018

Understanding Natural Language Commands for Robotic Navigation and Mobile Manipulation

Stefanie Tellex, Thomas Kollar, Steven Dickerson, Matthew R. Walter, Ashis G. Banerjee, Seth Teller, Nicholas Roy

Citations: 674 • 2011

Efficient grasping from RGBD images: Learning using a new rectangle representation

Jiang Yun, Stephen Moseson, Ashutosh Saxena

Citations: 662 • 2011

Maximum margin planning

Nathan Ratliff, J. Andrew Bagnell, Martin Zinkevich

Citations: 639 • 2006

Bayesian Online Changepoint Detection

Ryan P. Adams, David Mackay

Citations: 602 • 2007

Probabilistic data association for semantic SLAM

Sean L. Bowman, Nikolay Atanasov, Kostas Daniilidis, George J. Pappas

Citations: 474 • 2017

Probabilistic Graphical Models: Principles and Techniques - Adaptive Computation and Machine Learning

Daphne Koller, Nir Friedman

Citations: 472 • 2009

SIGMA: A Sparse and Irregular GEMM Accelerator with Flexible Interconnects for DNN Training

Eric Qin, Ananda Samajdar, Hyoukjun Kwon, Vineet Nadella, Sudarshan Srinivasan, Dipankar Das, Bharat Kaul, Tushar Krishna

Citations: 462 • 2020

Bayesian Map Learning in Dynamic Environments

Kevin P. Murphy

Citations: 451 • 1999

Reinforcement Learning with Deep Energy-Based Policies

Tuomas Haarnoja, Haoran Tang, Pieter Abbeel, Sergey Levine

Citations: 434 • 2017

The Replica Dataset: A Digital Replica of Indoor Spaces

Julian Straub, Thomas J. Whelan, Lingni Ma, Yufan Chen, Erik Wijmans, Simon Green, Jakob Julian Engel, Raul Mur-Artal, Carl Yuheng Ren, Shobhit Verma, Anton Clarkson, Mingfei Yan, Brian Budge, Yajie Yan, Xiaqing Pan, June Yon, Yuyang Zou, K Harding Leon, Jesús Briales, Tyler Z. Gillingham, Elias Mueggler, Luis Pesqueira, Manolis Savva, Dhruv Batra, Hauke Strasdat, Renzo De Nardi, Michael Goesele, Steven Lovegrove, Richard A. Newcombe

Citations: 384 • 2019

Semantic mapping for mobile robotics tasks: A survey

Ioannis Kostavelis, Αντώνιος Γαστεράτος

Citations: 373 • 2014

PaLM-E: An Embodied Multimodal Language Model

Danny Driess, Fei Xia, Mehdi S. M. Sajjadi, Corey Lynch, Aakanksha Chowdhery, Brian Ichter, Ayzaan Wahid, Jonathan Tompson, Quan Vuong, Tianhe Yu, Wenlong Huang, Yevgen Chebotar, Pierre Sermanet, Daniel Duckworth, Sergey Levine, Vincent Vanhoucke, Karol Hausman, Marc Toussaint, Klaus Greff, Andy Zeng, Igor Mordatch, Pete Florence

Citations: 350 • 2023

TensorFlow: learning functions at scale

Martı́n Abadi

Citations: 336 • 2016

Semantic Labeling of 3D Point Clouds for Indoor Scenes

Hema Swetha Koppula, Abhishek Anand, Thorsten Joachims, Ashutosh Saxena

Citations: 331 • 2011

Robot trajectory optimization using approximate inference

Marc Toussaint

Citations: 329 • 2009

Evolving Connectionist Systems: The Knowledge Engineering Approach

Nikola Kasabov

Citations: 325 • 2007