Autonomously constructing hierarchical task networks for planning and human-robot collaboration

By Bradley Hayes, Brian Scassellati. 2016

123 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Control and Systems Engineering

How researchers see this paper

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

In Artificial Intelligence

In Control and Systems Engineering

Citations in the corpus

Improving Robot Controller Transparency Through Autonomous Policy Explanation (2017, background): “Autonomous symbol abstraction techniques [16, 27] may also be applied to the learned domain MDPs, reducing the programmer’s workload with respect to annotating actions within the control software.”
Using General-Purpose Planning for Action Selection in Human-Robot Interaction (2016, methodology): “Beyond the bartender domain, we are also planning to apply such models in collaborative contexts, where a variety of planning techniques are already being applied (Freedman and Fukunaga 2015; Hayes and Scassellati 2016; Geib, Craenen, and Petrick 2016).”
Procedure Planning in Instructional Videos (2019, background): “Our insight is to leverage the conjugate relationship between states and actions [10] to provide further constraints on f(·) and g(·) and improve the optimization of LT .”
The grand challenges of Science Robotics (2018, background): “Modern work on intent recognition (79), user modeling in intelligent tutoring systems (80), collaboration models in humanmachine interaction (81), emotion recognition via facial feature analysis (82), and other domains touch on single aspects of this problem, but none of these domains has yet produc”
Recent Advances in Robot Learning from Demonstration (2020, background): “In addition to learning to autonomously perform tasks in different areas, LfD has been explored to provide manipulators with the ability to collaborate with humans in close proximity (14, 63, 66, 75, 84, 102, 133).”
A Review of Robot Learning for Manipulation: Challenges, Representations, and Algorithms (2019, background): “In some cases these result in a natural and intuitive form of incremental policy repair and generalization [281, 150].”
LanCon-Learn: Learning with Language to Enable Generalization in Multi-Task Manipulation (2021, background): “One popular approach to multi-task RL is to employ hierarchical [23], [47] or modular neural networks [31], [48], [2].”
Neural Task Graphs: Generalizing to Unseen Tasks From a Single Video Demonstration (2018, methodology): “We thus work with the conjugate task graph(CTG) [16], G = {V,E}, where the actions are now the nodes V , and the states become edges E, which implicitly encode the preconditions of the actions.”