Apprenticeship learning for motion planning with application to parking lot navigation

By Pieter Abbeel, Dmitri A. Dolgov, Andrew Y. Ng, Sebastian Thrun. 2008

143 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition, 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 Aerospace Engineering

In Computer Vision and Pattern Recognition

In Control and Systems Engineering

Citations in the corpus

Comparing human-centric and robot-centric sampling for robot deep learning from demonstrations (2016, neutral): “supervisor [14], [2], [5], [16], [12].”
Planning and Decision-Making for Autonomous Vehicles (2018, background): “(112) demonstrated an improved version of the algorithm and its performance by generating humanlike trajectories in parking lots, with only a few demonstrations required during learning.”
Predicting actions to act predictably: Cooperative partial motion planning with maximum entropy models (2016, background): “In [17], they further develop the algorithm and its performance is demonstrated on a”
From perception to decision: A data-driven approach to end-to-end motion planning for autonomous ground robots (2016, background): “[8] showed the application of apprenticeship learning for learning human’s navigation strategies on a parking lot.”
Probabilistic model-based imitation learning (2013, background): “, parking lot navigation [1] or quadruped locomotion [20]).”
Learning GP-BayesFilters via Gaussian process latent variable models (2009, background): “…is similar in spirit to other robot imitation learning systems, such as Grimes and Rao (2008) where a humanoid robot learns from human demonstrations, Ekvall and Kragic (2004) where robot grasps are learned from human trials, or Abbeel et al. (2008) where a robotic car learns from human drivers.”
A survey of inverse reinforcement learning techniques (2012, methodology): “Using similar ideas, a navigation controller was developed that enables a real size robotic car to learn different parking styles (Abbeel et al., 2008).”
Reinforced Imitation: Sample Efficient Deep Reinforcement Learning for Mapless Navigation by Leveraging Prior Demonstrations (2018, background): “[9] present an IRL-based approach where they teach an autonomous car to navigate in parking lots by observing human demonstrations.”
A Survey of State-Action Representations for Autonomous Driving (2018, background): “Likewise Abbeel et al. (2008); Ziebart et al. (2008); Stiller and Ziegler (2012); Gindele et al. (2015) represent the road network as a graph and and use it to evaluate the cost of the ego-vehicle’s planned trajectory.”
IRLAS: Inverse Reinforcement Learning for Architecture Search (2018, background): “Direct policy imitating between the feature counts of sampled architecture and expert network will raise a strong prior on the search space and force the agent to ‘mimic’ the expert [3, 2], which does not meet our expectation.”
Learning strategies in table tennis using inverse reinforcement learning (2014, methodology): “In the following, we will refer to this algorithm as MMG (Maximum Margin for Game values).”