Planning with approximate preferences and its application to disambiguating human intentions in navigation

Neumany, Bradford; Likhachevy, Maxim

doi:10.1109/icra.2013.6630609

Cited by 4 publications

(4 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Those then serve to train models that will predict the trajectory of a human based on online observations. Typically, a dense discretization of the space is applied, see, e.g., [ 6 , 7 , 8 , 9 ]. Within the works of [ 10 , 11 ], the discretization issue is addressed by learning a topological map, which summarizes a set of observed (person) trajectories.…”

Section: Related Workmentioning

confidence: 99%

“…In contrast to these works, in an indoor environment these cues are typically not available and instead of learning the static context within our work we explicitly model it. Looking at the robotics domain, the idea of considering the plausible alternatives for human intentions is in line with [ 8 , 19 , 25 ]. Within the first of these works, hypotheses about occupied areas in the map are created by considering various trajectories.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

A Probabilistic Model for Real-Time Semantic Prediction of Human Motion Intentions from RGBD-Data

Houtman

Bijlenga

Torta

et al. 2021

Sensors

View full text Add to dashboard Cite

For robots to execute their navigation tasks both fast and safely in the presence of humans, it is necessary to make predictions about the route those humans intend to follow. Within this work, a model-based method is proposed that relates human motion behavior perceived from RGBD input to the constraints imposed by the environment by considering typical human routing alternatives. Multiple hypotheses about routing options of a human towards local semantic goal locations are created and validated, including explicit collision avoidance routes. It is demonstrated, with real-time, real-life experiments, that a coarse discretization based on the semantics of the environment suffices to make a proper distinction between a person going, for example, to the left or the right on an intersection. As such, a scalable and explainable solution is presented, which is suitable for incorporation within navigation algorithms.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

A Probabilistic Model for Real-Time Semantic Prediction of Human Motion Intentions from RGBD-Data

Houtman

Bijlenga

Torta

et al. 2021

Sensors

View full text Add to dashboard Cite

show abstract

“…Clear preferences Under the clear preferences assumption (Likhachev and Stentz 2009;Neuman and Likhachev 2013), for any action with more than one outcome, we are given an outcome which is "clearly preferred" over the other outcomes. Specifically, for any state x and action a, the clearly-preferred outcome x satisfies the following condition,…”

Section: Probabilistic Planning With Clear Preferencesmentioning

confidence: 99%

Intuitive, Reliable Plans with Contingencies: Planning with Safety Nets for Landmark-Based Routing

Alwala

Safonova

Salzman

et al. 2021

SOCS

View full text Add to dashboard Cite

We are interested in the problem of providing intuitive instructions for human agents to enable reliable navigation in unknown environments. Since the advent of GPS and digital maps, a common approach is to visually provide a planned path on a digital map defined in terms of actions to take at specific junctions. However, this approach relies on the agent to constantly and accurately localize itself. Furthermore, it comes in stark contrast to the way humans provide instructions—by leveraging known landmarks in the environment to both augment the description of the planned path as well as to allow to detect when the agent deviated from the planned path. Hence, there is need for assurable means of localization, an intuitive way of compactly conveying directions to agents and a systematic approach to account for human errors. To this end, our key insight is to employ known landmarks in the environment to overcome these challenges. We formally model this intuitive way to use landmarks for conveying instructions and for creating contingency plans. We present experiments demonstrating the efficacy of our approach both on synthetic environments as well as on realworld maps, computed using a smart-phone iOS application that we developed.

show abstract

“…Ok et al [13] develop a path planner called Voronoi Uncertainty Fields, which uses Voronoi diagrams and potential fields to deal with map uncertainties. Neumany and Likhachevy [12] design a generalization to the PPCP (Probabilistic Planning with Clear Preferences) algorithm, which allows a robot to reason about uncertainty in the trajectories of dynamic obstacles. Sonti et al [16] present a grid-based path planning algorithm using probabilistic finite state automata (PFSA), and address the routing problems in the presence of dynamic obstacles with stochastic motion models.…”

Section: Introductionmentioning

confidence: 99%

Path Planning for First Responders in the Presence of Moving Obstacles With Uncertain Boundaries

Wang

Zlatanova

Oosterom

2017

IEEE Trans. Intell. Transport. Syst.

View full text Add to dashboard Cite

In this paper, we study the path planning for first responders in the presence of uncertain moving obstacles. To support the path planning, in our research we use hazard simulation to provide the predicted information of moving obstacles. A major problem in using hazard simulation is that the simulation results may involve uncertainty due to model errors or noise in the real measurements. To address this problem, we provide an approach to handle the uncertainty in the information of moving obstacles, and apply it to the case of toxic plumes. Our contribution consists of two parts: 1) a spatial data model that support representation of uncertain obstacles from hazard simulations and their influence on the road network; 2) a modified A* algorithm that can deal with the uncertainty and generate fast and safe routes passing though the obstacles. The experimental results show the routing capability of our approach and its potential for the application to real disasters.

show abstract

Planning with approximate preferences and its application to disambiguating human intentions in navigation

Cited by 4 publications

References 14 publications

A Probabilistic Model for Real-Time Semantic Prediction of Human Motion Intentions from RGBD-Data

A Probabilistic Model for Real-Time Semantic Prediction of Human Motion Intentions from RGBD-Data

Intuitive, Reliable Plans with Contingencies: Planning with Safety Nets for Landmark-Based Routing

Path Planning for First Responders in the Presence of Moving Obstacles With Uncertain Boundaries

Contact Info

Product

Resources

About