Guiding Trajectory Optimization by Demonstrated Distributions

By Takayuki Osa, Amir G. Esfahani, Rustam Stolkin, Rudolf Lioutikov, Jan Peters, Gerhard Neumann. 2017

63 citations recorded by the source corpus.

Trajectory optimization is an essential tool for motion planning under multiple constraints of robotic manipulators. Optimization-based methods can explicitly optimize a trajectory by leveraging prior knowledge of the system and have been used in various applications such as collision avoidance. However, these methods often require a hand-coded cost function in order to achieve the desired behavior. Specifying such cost function for a complex desired behavior, e.g., disentangling a rope, is a nontrivial task that is often even infeasible. Learning from demonstration (LfD) methods offer an alternative way to program robot motion. LfD methods are less dependent on analytical models and instead learn the behavior of experts implicitly from the demonstrated trajectories. However, the problem of adapting the demonstrations to new situations, e.g., avoiding newly introduced obstacles, has not been fully investigated in the literature. In this letter, we present a motion planning framework that combines the advantages of optimization-based and demonstration-based methods. We learn a distribution of trajectories demonstrated by human experts and use it to guide the trajectory optimization process. The resulting trajectory maintains the demonstrated behaviors, which are essential to performing the task successfully, while adapting the trajectory to avoid obstacles. In simulated experiments and with a real robotic system, we verify that our approach optimizes the trajectory to avoid obstacles and encodes the demonstrated behavior in the resulting trajectory.

Subfields: Artificial Intelligence, 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 Artificial Intelligence

In Computer Vision and Pattern Recognition

In Control and Systems Engineering

Citations in the corpus

Learning Self-Correctable Policies and Value Functions from Demonstrations with Negative Sampling (2019, methodology): “Imitation learning is commonly adopted as a standard approach in robotics (Pomerleau, 1989; Schaal, 1997; Argall et al., 2009; Osa et al., 2017; Ye & Alterovitz, 2017; Aleotti & Caselli, 2006; Lawitzky et al., 2012; Torabi et al., 2018; Le et al., 2017; 2018) and many other areas such as playing gam”
An Algorithmic Perspective on Imitation Learning (2018, methodology): “and it is hard to define the reward manually including, learning to drive a car by demonstration [Pomerleau, 1988] and complex manipulation such as knot-tying [Osa et al., 2017b].”
Kernelized movement primitives (2017, unknown): “ [3]. In order to capture the probabilistic distribution of demonstrations, a number of algorithms can be employed, such as GMM [2], hidden Markov models [13], and even a single Gaussian distribution [14], which differ in the type of information that is extracted from the demonstrations. For sake of”
Towards Robust Skill Generalization: Unifying Learning from Demonstration and Motion Planning (2017, methodology): “[20] carry out a functional gradient-based optimization for reproduction similar to CHOMP.”