E-Graphs: Bootstrapping Planning with Experience Graphs
By Mike Phillips, Benjamin J. Cohen, Sachin Chitta, Maxim Likhachev. 2012
108 citations recorded by the source corpus.
In this paper, we develop an online motion planning approach which learns from its planning episodes (experiences) a graph, an Experience Graph. On the theoretical side, we show that planning with Experience graphs is complete and provides bounds on suboptimality with respect to the graph that represents the original planning problem. Experimentally, we show in simulations and on a physical robot that our approach is particularly suitable for higher-dimensional motion planning tasks such as planning for two armed mobile manipulation.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Reinforcement Learning
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
- Sergey Levine
- Pieter Abbeel
- J. Bagnell
- Ashutosh Saxena
- Chelsea Finn
- Siddhartha S. Srinivasa
- Nathan D. Ratliff
- Jan Peters
In Computer Vision and Pattern Recognition
- Luc Van Gool
- Ashutosh Saxena
- Dieter Fox
- Jitendra Malik
- Kristen Grauman
- Li Fei-Fei
- Abhinav Kumar Gupta
- Dacheng Tao
In Reinforcement Learning
- Sergey Levine
- J. Bagnell
- Pieter Abbeel
- Chelsea Finn
- Siddhartha S. Srinivasa
- Nathan D. Ratliff
- Jan Peters
- Thorsten Joachims
Citations in the corpus
- Learning Trajectory Preferences for Manipulators via Iterative Improvement (2013, background): “User preferences have been studied in the field of human-robot interaction.”
- CHOMP: Covariant Hamiltonian optimization for motion planning (2013, methodology): “Additional work has examined inducing smoother motion while reducing the cardinality of the action set [13], as well as re-using partial plans discovered by past searches [59].”
- Alternative Paths Planner (APP) for Provably Fixed-time Manipulation Planning in Semi-structured Environments (2020, methodology): “6, 414) E-Graphs [8] 988 1044 904 203 273 275 162 210 176”