Learning Bayesian filters without precise ground truth

21 January 2011

share this:

As seen in a previous post, Bayes filters such as Kalman filters can be used to estimate the state of a robot. Usually, this requires having a model of how the robot’s sensor measurements relate to the state you want to observe and a model to predict how the robot’s control inputs impact its state. When little is know about these models, machine learning techniques can help find models automatically.

In the scenario imagined by Ko et al. the goal is to infer a car’s position (state) on a race track based on remote control commands and measurements from an Inertial Measurement Unit (IMU, see red box in picture below) that provides turn rates in roll, pitch, and yaw and accelerations in 3 dimensions. The car is only controlled in speed since a “rail” in the track makes it turn. As a start, Ko et al. collect data by driving the car around the track while recording its remote control commands, IMU measurements, and position (ground truth) estimated using an overhead camera. The data is then used to train probabilistic models (Gaussian Process models) that are finally integrated into a Bayes filter.

However, the need for ground truth requires extra effort and additional hardware such as the overhead camera. To overcome this problem, Ko et al. extend their method to deal with situations where no, little, or noisy ground truth is used to train the models.

Results show the successful tracking of the car with better performance than state-of-the-art approaches, even when no ground truth is given. The authors also show how the developed method can be used to allow the car or a robot arm to replay trajectories based on expert demonstrations.

Sabine Hauert is President of Robohub and Associate Professor at the Bristol Robotics Laboratory
Sabine Hauert is President of Robohub and Associate Professor at the Bristol Robotics Laboratory

Related posts :

How robots learn to hike

A new control approach that enables a legged robot, called ANYmal, to move quickly and robustly over difficult terrain.
20 January 2022, by

How robots and bubbles could soon help clean up underwater litter

Everyone loves to visit the seaside, whether to enjoy the physical benefits of an exhilarating swim or simply to relax on the beach and catch some sun. But these simple life affirming pleasures are easily ruined by the presence of litter, which if persistent can have a serious negative impact on both the local environment and economy. However, help is at hand to ensure the pristine nature of our coastlines.
19 January 2022, by

Maria Gini wins the 2022 ACM/SIGAI Autonomous Agents Research Award

Congratulations to Maria Gini on winning this prestigious award, recognising her research and leadership in the field of robotics and multi-agent systems.
18 January 2022, by

UN fails to agree on ‘killer robot’ ban as nations pour billions into autonomous weapons research

Given the pace of research and development in autonomous weapons, the U.N. meeting might have been the last chance to head off an arms race.
16 January 2022, by

Science Magazine robot videos 2021

A compilation of Science Magazine videos featuring robotics research that were released during last year.
14 January 2022, by

CBQ: Commercial-grade Autonomous Mowers, Safety, and Dogfooding | Sense Think Act Podcast #11

In this episode, Audrow Nash speaks to Charles Brian Quinn (aka, CBQ), CEO and a Co-Founder of Greenzie. Greenzie make an autonomous driving system for commercial lawn mowers. We talk about Greenzie's...
11 January 2022, by and

©2021 - ROBOTS Association


©2021 - ROBOTS Association