Noel E. Du Toit's research while affiliated with California Institute of Technology and other places

Publications (5)

Article
This paper presents a strategy for planning robot motions in dynamic, uncertain environments (DUEs). Successful and efficient robot operation in such environments requires reasoning about the future evolution and uncertainties of the states of the moving agents and obstacles. A novel procedure to account for future information gathering (and the qu...
Article
Obstacle avoidance, and by extension collision checking, is a basic requirement for robot autonomy. Most classical approaches to collision-checking ignore the uncertainties associated with the robot and obstacle’s geometry and position. It is natural to use a probabilistic description of the uncertainties. However, constraint satisfaction cannot be...
Conference Paper
This paper presents a strategy for planning robot motions in dynamic, cluttered, and uncertain environments. Successful and efficient operation in such environments requires reasoning about the future system evolution and the uncertainty associated with obstacles and moving agents in the environment. This paper presents a novel procedure to account...
Article
This thesis is concerned with robot motion planning in dynamic, cluttered, and uncertain environments. Successful and efficient robot operation in such environments requires reasoning about the future system evolution and the uncertainty associated with obstacles and moving agents in the environment. Current motion planning strategies ignore future...
Article
Full-text available
Robot navigation in urban environments requires situational reasoning. Given the complexity of the environment and the behavior specified by traffic rules, it is necessary to recognize the current situation to impose the correct traffic rules. In an attempt to manage the complexity of the situational reasoning subsystem, this paper describes a fini...

Citations

... A comparison of our approach to different state-of-the-art methods are also provided. [65,113,82,19]. (a) The robot state (in blue) is known perfectly, however the obstacle location (in green) is uncertain. (b) Robot state uncertainty is considered. ...
... Exact collision probability can be computed by marginalizing the joint distribution between the robot and obstacle locations [18]. This integration is then performed over the set of robot and obstacle locations that satisfy the collision constraint. ...
... Motivated by the practical issues caused by the lack of predictive models, a second wave of efforts on the crowd navigation problem focused on methodologies for reasoning about uncertainty. For instance, Du Toit and Burdick [18] present a receding-horizon control framework that incorporates predictive uncertainty in the robot's decision making. Thompson et al. [70] introduce a probabilistic model of human motion based on individual human intent inference, designed to assist in motion planning problems. ...
... Respondents should be aware that notwithstanding any other provision of law, no person shall be subject to a penalty for failing to comply with a collection of information if it does not display a currently valid OMB control number. Prescribed by ANSI Std Z39-18 at the National Qualifying Event of the 2007 DARPA Urban Challenge [Burdick et al. 2007], [Wongpiromsarn and Murray 2008], [DuToit et al. 2008]. In executing the third task, which involved making left-turns while merging into traffic, its behavior was unsafe and almost led to a collision. ...
... In previous studies, Blackmore et al. proposed a chance constraints formulation for a system subject to Gaussian noise, by assuming that all environmental obstacles have static and deterministic locations [14,15]. Toit et al. developed a chance constrained framework that considered other types of uncertainties [16]. Luders et al. extended the chance constraints formulation to allow for dynamic and probabilistic obstacles [11]. ...