update offroad page

_posts/2022-08-08-offroad.md

@@ -87,14 +87,17 @@ Previous approaches for off-road traversability have focused on representing vis
 
 What we are really interested in capturing is roughness in traversability as the vehicle experienced it, rather than capturing the appearance or geometry of roughness. For instance, a point cloud of tall grass might appear rough, but traversing over this grass could still lead to smooth navigation if the terrain under the grass is smooth. 
 
-In our ICRA 2023 paper “How Does It Feel? Self-Supervised Costmap Learning for Off-Road Vehicle Traversability”, we propose a self-supervised method that predicts costmaps that reflect nuanced terrain interaction properties relevant to ground navigation. We approach this problem by learning a mapping from rich exteroceptive information and robot velocity to a continuous traversability cost derived from IMU data.
+In our [ICRA 2023 paper](https://arxiv.org/abs/2209.10788) “How Does It Feel? Self-Supervised Costmap Learning for Off-Road Vehicle Traversability”, we propose a self-supervised method that predicts costmaps that reflect nuanced terrain interaction properties relevant to ground navigation. We approach this problem by learning a mapping from rich exteroceptive information and robot velocity to a continuous traversability cost derived from IMU data.
 
 <figure>
  <img src="/img/posts/2023-08-08-offroad/hdif.png" alt="" />
 </figure>
 
 We find that our method outperforms occupancy-based baselines on short-scale and large-scale navigation trials. Our short-scale navigation results show that using our learned costmaps leads to overall smoother navigation, and provides the robot with a more fine-grained understanding of the interactions between the robot and different terrain types, such as grass and gravel. Our large-scale navigation trials show that we can reduce the number of interventions by up to 57% compared to an occupancy-based navigation baseline in challenging off-road courses ranging from 400 m to 3150 m. 
 
+{% youtube 19sDs1S8IGk %}
+
+
 ## Off-Road Driving through Imitating Human Experts
 Another source of unlabeled supervision for learning navigation behaviors are examples of teleoperation from human experts. Compared to human labeling of traversable and non-traversable terrain, collecting supervision by simply allowing humans to drive off-road dramatically simplifies and accelerates the data collection process.
 
@@ -104,8 +107,11 @@ In order to translate human-driven trajectories into a form consumable by planni
  <img src="/img/posts/2023-08-08-offroad/irl.png" alt="" />
 </figure>
 
-In order to achieve a practical algorithm that runs effectively on our platform, we leverage maximum entropy IRL (MaxEnt IRL) with several extensions, such as sampling-based MPC, risk estimation, and deep neural networks. We find that IRL significantly outperforms occupancy-based baselines on several kilometers of challenging off-road trails (reducing interventions by up to 70%). Furthermore, we find that we can leverage our risk-estimation to modulate how aggressive the ATV is with respect to terrains such as tall grass and slopes. Results are presented in our ICRA 2023 paper “Learning Risk-Aware Costmaps via Inverse Reinforcement Learning for Off-Road Navigation''. 
+In order to achieve a practical algorithm that runs effectively on our platform, we leverage maximum entropy IRL (MaxEnt IRL) with several extensions, such as sampling-based MPC, risk estimation, and deep neural networks. We find that IRL significantly outperforms occupancy-based baselines on several kilometers of challenging off-road trails (reducing interventions by up to 70%). Furthermore, we find that we can leverage our risk-estimation to modulate how aggressive the ATV is with respect to terrains such as tall grass and slopes. Results are presented in our [ICRA 2023 paper](https://arxiv.org/abs/2302.00134) “Learning Risk-Aware Costmaps via Inverse Reinforcement Learning for Off-Road Navigation''. 
 
+<!-- [![Watch the video]](https://drive.google.com/file/d/1SJqSMNusDhjc-EY9LCMec5UrZMVkxpa5/view?resourcekey) -->
+
+<iframe src="https://drive.google.com/file/d/1SJqSMNusDhjc-EY9LCMec5UrZMVkxpa5/preview" width="1024" height="720" allow="autoplay"></iframe>
 
 ## Learning Vehicle Dynamics
 
@@ -117,7 +123,7 @@ The Kinematic Bicycle Model (KBM), one of the examples of a model developed from
  <img src="/img/posts/2023-08-08-offroad/dynamicsmodel.png" alt="" style="width:80%" />
 </figure>
 
-We therefore employ deep learning to address this, which offers very expressive models for function approximation. We leverage real-time information from gps-based odometry along with multiple other modalities like, First-Person View Image, Heightmaps and RGB-maps.  By reducing the RMSE loss in the anticipated state - [x, y, yaw, velocity] (See Table 1. For deeper analysis), these models outperform purely physics-driven models. Our ICRA 2022 work, "TartanDrive: A Large-Scale Dataset for Learning Off-Road Dynamics Models," provides a thorough description of the model. 
+We therefore employ deep learning to address this, which offers very expressive models for function approximation. We leverage real-time information from gps-based odometry along with multiple other modalities like, First-Person View Image, Heightmaps and RGB-maps.  By reducing the RMSE loss in the anticipated state - [x, y, yaw, velocity] (See Table 1. For deeper analysis), these models outperform purely physics-driven models. Our [ICRA 2022 work](https://arxiv.org/abs/2205.01791), "TartanDrive: A Large-Scale Dataset for Learning Off-Road Dynamics Models" provides a thorough description of the model. 
 
 Table 1: Here we show RMSE errors of the last predicted point in a 2-second horizon
 
@@ -129,9 +135,9 @@ Table 1: Here we show RMSE errors of the last predicted point in a 2-second hori
 
 
 
+While DL-based models perform better than KBM, they do poorly generalize because they find it difficult to grasp the symmetries and conservation rules that underlie dynamical systems. Consideration of a hybrid method, which encodes physics, laws, and geometric aspects of the underlying system in the construction of the neural network architecture or in the learning process, has been a current study direction in the field and for us. The resulting "physics-informed neural networks" feature superior generalization capabilities, enhanced design, and efficiency. Please check out our [ICRA 2024 paper](https://arxiv.org/abs/2311.00815): "PIAug -- Physics Informed Augmentation for Learning Vehicle Dynamics for Off-Road Navigation". 
 
-
-While DL-based models perform better than KBM, they do poorly generalize because they find it difficult to grasp the symmetries and conservation rules that underlie dynamical systems. Consideration of a hybrid method, which encodes physics, laws, and geometric aspects of the underlying system in the construction of the neural network architecture or in the learning process, has been a current study direction in the field and for us. The resulting "physics-informed neural networks" feature superior generalization capabilities, enhanced design, and efficiency.
+{% youtube r0Dq61DIWZQ %}
 
 
 ## Online Adaptation for Off-road Driving