-
-
+
-
@@ -197,20 +197,19 @@
- +
Our algorithm consists of an offline learning phase and an online execution phase. During the offline phase, we learn a set of basis functions that span the space of dynamics. This space of dynamics can arise due to unknown system parameters, such as a quadrotor with an unknown mass. @@ -185,7 +185,7 @@
During the online phase, we use the learned basis functions and a small online dataset to identify the dynamics of the system. This online adaptation requires zero gradient updates, and can be computed in real-time. Then, this model can be used for downstream tasks, such as MPC. -
+
-
-
-
-
- Accurate Long Horizon Predictions
-
-
+
+
+
+
+
+ Accurate Long Horizon Predictions
-
We demonstrate that our learned models can accurately predict the dynamics on the MuJoCo HalfCheetah and Ant environments.
We vary numerous environment parameters, such as lengths of the limbs and the control authority.
Then, given a small online dataset, we attempt to predict the dynamics k steps into the future.
- Our results indicate that we achieve both the accurate long horizon predictions of neural ODEs and the online adaptability of function encoders.
+ Our results indicate that we achieve both the accurate long horizon predictions of neural ODEs and the online adaptability of
+ function encoders.
@@ -219,26 +218,20 @@
-
-
-
-
- Online, Adaptive MPC
-
-
+
+
+
+
+
-
We apply this algorithm to the MPC control of a quadrotor. The quadrotor's mass is varied every episode, and the goal is to reach prespecified coordinates.
Our results demonstrate that our approach makes more accurate long horizon predictions in the presence
of hidden parameters than neural ODEs alone. When measuring the slew rate of the controller, i.e. its efficiency, we observe that this improved prediction
accuracy leads to more efficient control of the quadrotor.
-
-
Qualitatively, this difference is visible in the trajectories of the respective controllers. Here we are plotting one trajectory from each controller
for the same conditions. We observe that the neural ODE controller alone makes repeated corrections to its trajectory. In contrast, our approach more smoothly
approaches the target coordinates.
-
-
-
-
Accurate Long Horizon Predictions
-
-
+
+
+
-
+
@@ -219,26 +218,20 @@
+
+
-
Accurate Long Horizon Predictions
- We demonstrate that our learned models can accurately predict the dynamics on the MuJoCo HalfCheetah and Ant environments. We vary numerous environment parameters, such as lengths of the limbs and the control authority. Then, given a small online dataset, we attempt to predict the dynamics k steps into the future. - Our results indicate that we achieve both the accurate long horizon predictions of neural ODEs and the online adaptability of function encoders. + Our results indicate that we achieve both the accurate long horizon predictions of neural ODEs and the online adaptability of + function encoders.
-
-
-
-
- Online, Adaptive MPC
-
-
+
+
+
+
+
-
We apply this algorithm to the MPC control of a quadrotor. The quadrotor's mass is varied every episode, and the goal is to reach prespecified coordinates.
Our results demonstrate that our approach makes more accurate long horizon predictions in the presence
of hidden parameters than neural ODEs alone. When measuring the slew rate of the controller, i.e. its efficiency, we observe that this improved prediction
accuracy leads to more efficient control of the quadrotor.
-
-
Qualitatively, this difference is visible in the trajectories of the respective controllers. Here we are plotting one trajectory from each controller
for the same conditions. We observe that the neural ODE controller alone makes repeated corrections to its trajectory. In contrast, our approach more smoothly
approaches the target coordinates.
-
-
-
-
Online, Adaptive MPC
-
-
+
+
+
+
+
-
-
- We apply this algorithm to the MPC control of a quadrotor. The quadrotor's mass is varied every episode, and the goal is to reach prespecified coordinates. Our results demonstrate that our approach makes more accurate long horizon predictions in the presence of hidden parameters than neural ODEs alone. When measuring the slew rate of the controller, i.e. its efficiency, we observe that this improved prediction accuracy leads to more efficient control of the quadrotor. -
-