PMTG Baseline
We demonstrate a working implementation of Policies Modulating Trajectory Generators (Iscen et al. 2019) on the MIT Mini Cheetah. When the trajectory generator is tuned to accommodate more dynamic behaviors, unrealistic and non-robust motion artifacts emerge in simulation due to the implicit treatment of force.
Successful PMTG Deployment (Flat Terrain)
![](https://www.google.com/images/icons/product/drive-32.png)
Forward Trot
![](https://www.google.com/images/icons/product/drive-32.png)
Testing robustness against external push
PMTG Simulation Results (Gap Terrain)
Relaxed TG Parameters enable longer gap crossing, but introduce undesired gait characteristics such as missed contacts and rapid changes in roll and pitch.
Pronking
![](https://www.google.com/images/icons/product/drive-32.png)
Conservative TG parameters
Max Gap Width : 15cm
![](https://www.google.com/images/icons/product/drive-32.png)
Relaxed TG parameters
Max Gap Width : 25cm
Trotting
![](https://www.google.com/images/icons/product/drive-32.png)
Conservative TG parameters
Max Gap Width : 10cm
![](https://www.google.com/images/icons/product/drive-32.png)
Relaxed TG parameters
Max Gap Width : 15cm
Trajectory Plots
PMTG without Specialized Rewards (Gap Terrain)
We found that PMTG baseline requires specialized reward design and extensive tuning for traversing gaps larger than 10cm in case of Trotting and 20cm in case of Pronking. Otherwise, it leads to unsuccessful gap crossing behaviors such as gap avoidance or in-place motion.
![](https://www.google.com/images/icons/product/drive-32.png)
Gap Width : 10cm
![](https://www.google.com/images/icons/product/drive-32.png)
Gap Width : 20cm