Differentiable Gaussian Process Motion Planning

By Mohak Bhardwaj, Byron Boots, Mustafa Mukadam. 2019

71 citations recorded by the source corpus.

Modern trajectory optimization based approaches to motion planning are fast, easy to implement, and effective on a wide range of robotics tasks. However, trajectory optimization algorithms have parameters that are typically set in advance (and rarely discussed in detail). Setting these parameters properly can have a significant impact on the practical performance of the algorithm, sometimes making the difference between finding a feasible plan or failing at the task entirely. We propose a method for leveraging past experience to learn how to automatically adapt the parameters of Gaussian Process Motion Planning (GPMP) algorithms. Specifically, we propose a differentiable extension to the GPMP2 algorithm, so that it can be trained end-to-end from data. We perform several experiments that validate our algorithm and illustrate the benefits of our proposed learning-based approach to motion planning.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Software, Probabilistic & Bayesian Methods, Robotics & Control

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

1. Dhruv Batra
2. Trevor Darrell
3. Abhinav Kumar Gupta
4. Jitendra Malik
5. Vladlen Koltun
6. Sergey Levine
7. Kristen Grauman
8. Ruslan Salakhutdinov

In Computer Vision and Pattern Recognition

1. Dhruv Batra
2. Jitendra Malik
3. Luc Van Gool
4. Abhinav Kumar Gupta
5. Trevor Darrell
6. Kristen Grauman
7. Dacheng Tao
8. Andrew Zisserman

In Software

1. Jitendra Malik
2. Vladlen Koltun
3. David Hsu
4. Dhruv Batra
5. Shaojun Cai

In Probabilistic & Bayesian Methods

1. Jitendra Malik
2. Vladlen Koltun
3. Zsolt Kira
4. David Hsu
5. Dhruv Batra
6. Peter Karkus
7. Mustafa Mukadam
8. Shaojun Cai

In Robotics & Control

1. Dhruv Batra
2. Manolis Savva
3. Vladlen Koltun
4. Devendra Singh Chaplot
5. Jitendra Malik
6. Angel X. Chang
7. David Hsu
8. Peter Karkus

Citations in the corpus

• Habitat 2.0: Training Home Assistants to Rearrange their Habitat (2021, methodology): “[99] Mohak Bhardwaj, Byron Boots, and Mustafa Mukadam.”
• Differentiable SLAM-net: Learning Particle SLAM for Visual Navigation (2021, background): “Differentiable algorithms are emerging for a wide range of learning domains, including state estimation [24; 31; 34; 42], visual mapping [23; 36], planning [55; 33; 18; 49; 22; 62] and control tasks [2; 50; 17; 6].”