## Is Robotics Going Statistics? The Field of Probabilistic Robotics

Citations: | 8 - 3 self |

### BibTeX

@MISC{Thrun_isrobotics,

author = {Sebastian Thrun},

title = {Is Robotics Going Statistics? The Field of Probabilistic Robotics},

year = {}

}

### OpenURL

### Abstract

In the 1970s, most research in robotics presupposed the availability of exact models, of robots andtheir environments. Little emphasis was placed on sensing and the intrinsic limitations of modeling complex physical phenomena. This changed in the mid-1980s, when the paradigm shifted towardsreactive techniques. Reactive controllers rely on capable sensors to generate robot control. Rejections of models were typical for researchers in this field. Since the mid-1990s, a new approach has begunto emerge: probabilistic robotics. This approach relies on statistical techniques to seamlessly integrate imperfect models and imperfect sensing. The present article describes the basics of probabilistic roboticsand highlights some of its recent successes.

### Citations

1046 |
The EM algorithm and extensions
- McLachlan, Krishnan
- 1997
(Show Context)
Citation Context ...e nature of the state estimation problem. In the robotic mapping problem, two of the most widely used algorithms are extended Kalman filters (EKFs) [5] and the expectation maximization (EM) algorithm =-=[6]-=-. Extended Kalman filters are applicable when the posterior can reasonably assumed to be Gaussian. This is usually the case when mapping the locations of landmarks that can be uniquely identified. Kal... |

348 |
The optimal control of partially observable Markov processes over the infinite horizon: Discounted costs
- Sondik
- 1978
(Show Context)
Citation Context ...late the probability that any state x is correct. Popular examples of Bayes filters are hidden Markov models, Kalman filters, dynamic Bayes networks and partially observable Markov decision processes =-=[5, 10]-=-. For low-dimensional state spaces, research in robotics and applied statistics has produced a wealth of literature on efficient probabilistic estimation. Remarkably popular is an algorithm known as p... |

258 |
Stochastic Models, Estimation and Control, Volume 1
- Maybeck
- 1979
(Show Context)
Citation Context ...late the probability that any state x is correct. Popular examples of Bayes filters are hidden Markov models, Kalman filters, dynamic Bayes networks and partially observable Markov decision processes =-=[5, 10]-=-. For low-dimensional state spaces, research in robotics and applied statistics has produced a wealth of literature on efficient probabilistic estimation. Remarkably popular is an algorithm known as p... |

160 | Probabilistic algorithms and the interactive museum tour-guide robot Minerva
- Thrun, Beetz, et al.
- 2000
(Show Context)
Citation Context ...Three examples of successful robot systems that operate in uncertain environments are shown in Figure 1: a commercially deployed autonomous straddle carrier [3], an interactive museum tourguide robot =-=[7, 11]-=-, and a prototype robotic assistant for the elderly. The straddle carrier is capable of transporting containers faster than trained human operators. The tourguide robot—one in a series of many—can saf... |

160 | Sequential Monte Carlo Methods - Doucet, Freitas, et al. - 2001 |

143 | Coordination for multi-robot exploration and mapping
- Simmons, Apfelbaum, et al.
- 2000
(Show Context)
Citation Context ...approach was successfully employed to prevent the robot from falling down staircases. Similar techniques have been successfully brought to bear for active environment exploration with teams of robots =-=[9]-=-, using payoff functions that measure the residual uncertainty in the map. Non-greedily optimizing robot control—over multiple time steps—remains a challenging computational problem. This is because t... |

82 | Coastal navigation with mobile robots
- Roy, Thrun
- 2000
(Show Context)
Citation Context ...a most challenging planning problem [10]. Nevertheless, recent research has led to a flurry of approximate algorithms that are computationally efficient. The coastal navigation algorithm described in =-=[8]-=- condenses the posterior belief to two quantities: the most likely state, and the entropy of the posterior. This state space representation is exponentially more compact than the space of all posterio... |

67 | The EM Algorithm and Extensions. Wiley series in probability and statistics - McLachlan, Krishnan - 1997 |

46 |
Using EM to learn 3D models with mobile robots
- Liu, Emery, et al.
- 2001
(Show Context)
Citation Context ...a) has been generated through an on-line variant of the EM algorithm, accommodating errors in the robot odometry and exploiting a Bayesian prior that biases the resulting maps towards planar surfaces =-=[4]-=-. In all these applications, probabilistic model selection techniques are employed for finding models of the “right” complexity. 5 Probabilistic Planning and Control State estimation is only half the ... |

42 |
An Experimental and Theoretical Investigation into Simultaneous Localization and Map Building
- Dissanayake, Newman, et al.
(Show Context)
Citation Context ...s the location of walls, doors, and objects of interest. This problem, known as mapping, is regarded one of the most difficult state estimation due to the high dimensionality of such parameter spaces =-=[1]-=-, and • parameters of objects whose position changes over time, such as people, doors, and other robots. This problem is similar to the mapping problem, with the added difficulty changing locations ov... |

31 |
An autonomous guided vehicle for cargo handling applications
- Durrant-Whyte
- 1996
(Show Context)
Citation Context ...allenges faced by robotics research today. Three examples of successful robot systems that operate in uncertain environments are shown in Figure 1: a commercially deployed autonomous straddle carrier =-=[3]-=-, an interactive museum tourguide robot [7, 11], and a prototype robotic assistant for the elderly. The straddle carrier is capable of transporting containers faster than trained human operators. The ... |

26 |
Towards terrain-aided navigation for underwater robotics
- Williams, Dissanayake, et al.
- 2001
(Show Context)
Citation Context ...taneously estimating the location of the robot relative to the map [1]. Figure 3(b) shows an example map of landmarks in an underwater environment, obtained by researchers at the University of Sydney =-=[12]-=-. In the general mapping problem, the desired posterior may have exponentially many modes—not just one. Different modes commonly arise from uncertainty in calculating the correspondence between map it... |

7 |
An affective mobile robot with a fulltime job
- Nourbakhsh
- 1999
(Show Context)
Citation Context ...Three examples of successful robot systems that operate in uncertain environments are shown in Figure 1: a commercially deployed autonomous straddle carrier [3], an interactive museum tourguide robot =-=[7, 11]-=-, and a prototype robotic assistant for the elderly. The straddle carrier is capable of transporting containers faster than trained human operators. The tourguide robot—one in a series of many—can saf... |

1 | An experimental andtheoretical investigation into simultaneous localisation and map building (SLAM - Dissanayake, Newman, et al. - 2000 |