Probabilistic Robotics (Intelligent Robotics and Autonomous Agents)

By Sebastian Thrun, Wolfram Burgard, Dieter Fox. 2005

2,752 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Recurrent Neural Filters: Learning Independent Bayesian Filtering Steps for Time Series Prediction (2019, methodology): “Performing inference via a series of prediction and update steps (Sarkka, 2013), Bayes ﬁlters recursively update the posterior distribution of predictions – or the belief state (Thrun et al., 2005) – with the arrival of new data.”
Interactive Fiction Games: A Colossal Adventure (2019, methodology): “This gives rise to the Textual-SLAM problem, a textual variant of Simultaneous localization and mapping (SLAM) [Thrun et al., 2005] problem of constructing a map while navigating a new environment.”
Intrinsically motivated information foraging (2010, unknown): “For this reason [15] recommended taking a purely greedy, one-step information maximization approach instead of trying to maximize long-term information gain in POMDPs.”
KnowRob: A knowledge processing infrastructure for cognition-enabled robots (2013, methodology): “Statistical models have become an indispensable tool in robotics for representing such uncertain information (Thrun et al., 2005), for example for solving the localization and mapping problem by representing the probability distribution over the robot’s location using particle filters.”
Multi-modal estimation with kernel embeddings for learning motion models (2013, background): “…of robotics are the ubiquitous Kalman filter [1] which is restricted to linear models and normally-distributed variables, the extended and unscented Kalman filters [2], [3] which admit non-linear models, and the particle filter [4] which admits both non-linear models and non-Gaussian distributions.”
A survey of deep learning techniques for autonomous driving (2019, background): “Popular in robotics [72], [75], the OG representation became a suitable solution for selfdriving vehicles.”
Optical techniques for 3D surface reconstruction in computer-assisted laparoscopic surgery (2013, background): “Readers are directed to (Thrun et al., 2005) for detailed mathematical descriptions.”
Statistical Relational Learning of Object Affordances for Robotic Manipulation (2011, background): “Therefore, much of current robotics research is concerned with probabilistic reasoning and learning techniques [10] instead of symbolic representations.”
Active vision for dexterous grasping of novel objects (2016, background): “where ot+1 ∈ O = {occupied, free} is an imaginary future measurement and L(sd|o) is also called inverse sensor model [21].”
It Is Not the Journey but the Destination: Endpoint Conditioned Trajectory Prediction (2020, background): “Predicting the movement of dynamic objects is a central problem for autonomous agents, be it humans, social robots [1], or self-driving cars [2].”
Predictive-Corrective Networks for Action Detection (2017, methodology): “We refer the reader to [41] for an overview of Kalman filters; for our purposes, we think of K as a learned non-linear function of the difference between actual and predicted frame appearance yt − ŷt|t−1.”
Random Walk Inference and Learning in A Large Scale Knowledge Base (2011, methodology): “LVS first generates a random number r in the interval [0,M−1].”
MOTChallenge: A Benchmark for Single-Camera Multiple Target Tracking (2020, methodology): “[Taskar et al., 2003]. MDP [Xiang et al., 2015] goes one step further and proposes to learn track management policies (birth/death/association) by modeling object tracks as Markov Decision Processes [Thrun et al., 2005]. Standard MOT evaluation measures [Stiefelhagen et al., 2006] are not dierentiab”
PointNetVLAD: Deep Point Cloud Based Retrieval for Large-Scale Place Recognition (2018, methodology): “A common method for the localization problem is to first store a map of the environment as a database of 3D point cloud built from a collection of images with Structure-from-Motion (SfM) [15], or LiDAR scans with Simultaneous Localization and Mapping (SLAM) [44].”
Planning-based prediction for pedestrians (2009, background): “Particle filters [16] can incorporate more sophisticated constraints and non-Gaussian distributions, but degrade into random walks of feasible motion over large time horizons rather than purposeful, goal-based motion.”