An official website of the United States government
We introduce GROOT, an imitation learning method for learning robust policies with object-centric and 3D priors. GROOT builds policies that generalize beyond their initial training conditions for vision-based manipulation. It constructs object-centric 3D representations that are robust toward background changes and camera views and reason over these representations using a transformer-based policy. Furthermore, we introduce a segmentation correspondence model that allows policies to generalize to new objects at test time. Through comprehensive experiments, we validate the robustness of GROOT policies against perceptual variations in simulated and real-world environments. GROOT's performance excels in generalization over background changes, camera viewpoint shifts, and the presence of new object instances, whereas both state-of-the-art end-to-end learning methods and object proposal-based approaches fall short. We also extensively evaluate GROOT policies on real robots, where we demonstrate the efficacy under very wild changes in setup.
more »
« less
Eagle: End-to-end Deep Reinforcement Learning based Autonomous Control of PTZ Cameras
Existing approaches for autonomous control of pan-tilt-zoom (PTZ) cameras use multiple stages where object detection and localization are performed separately from the control of the PTZ mechanisms. These approaches require manual labels and suffer from performance bottlenecks due to error propagation across the multi-stage flow of information. The large size of object detection neural networks also makes prior solutions infeasible for real-time deployment in resource-constrained devices. We present an end-to-end deep reinforcement learning (RL) solution called Eagle1 to train a neural network policy that directly takes images as input to control the PTZ camera. Training reinforcement learning is cumbersome in the real world due to labeling effort, runtime environment stochasticity, and fragile experimental setups. We introduce a photo-realistic simulation framework for training and evaluation of PTZ camera control policies. Eagle achieves superior camera control performance by maintaining the object of interest close to the center of captured images at high resolution and has up to 17% more tracking duration than the state-of-the-art. Eagle policies are lightweight (90x fewer parameters than Yolo5s) and can run on embedded camera platforms such as Raspberry PI (33 FPS) and Jetson Nano (38 FPS), facilitating real-time PTZ tracking for resource-constrained environments. With domain randomization, Eagle policies trained in our simulator can be transferred directly to real-world scenarios2.
more »
« less
- Award ID(s):
- 2211301
- PAR ID:
- 10464625
- Date Published:
- Journal Name:
- IoTDI '23: Proceedings of the 8th ACM/IEEE Conference on Internet of Things Design and Implementation
- Page Range / eLocation ID:
- 144 to 157
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Computationally efficient, camera-based, real-time human position tracking on low-end, edge devices would enable numerous applications, including privacy-preserving video redaction and analysis. Unfortunately, running most deep neural network based models in real time requires expensive hardware, making widespread deployment difficult, particularly on edge devices. Shifting inference to the cloud increases the attack surface, generally requiring that users trust cloud servers, and increases demands on wireless networks in deployment venues. Our goal is to determine the extreme to which edge video redaction efficiency can be taken, with a particular interest in enabling, for the first time, low-cost, real-time deployments with inexpensive commodity hardware. We present an efficient solution to the human detection (and redaction) problem based on singular value decomposition (SVD) background removal and describe a novel time- and energy-efficient sensor-fusion algorithm that leverages human position information in real-world coordinates to enable real-time visual human detection and tracking at the edge. These ideas are evaluated using a prototype built from (resource-constrained) commodity hardware representative of commonly used low-cost IoT edge devices. The speed and accuracy of the system are evaluated via a deployment study, and it is compared with the most advanced relevant alternatives. The multi-modal system operates at a frame rate ranging from 20 FPS to 60 FPS, achieves awIoU0.3score (see Section 5.4) ranging from 0.71 to 0.79, and successfully performs complete redaction of privacy-sensitive pixels with a success rate of 91%–99% in human head regions and 77%–91% in upper body regions, depending on the number of individuals present in the field of view. These results demonstrate that it is possible to achieve adequate efficiency to enable real-time redaction on inexpensive, commodity edge hardware.more » « less
-
Zhou, Jianhong; Osten, Wolfgang; Nikolaev, Dmitry P. (Ed.)Despite recent advances in deep learning, object detection and tracking still require considerable manual and computational effort. First, we need to collect and create a database of hundreds or thousands of images of the target objects. Next we must annotate or curate the images to indicate the presence and position of the target objects within those images. Finally, we must train a CNN (convolution neural network) model to detect and locate the target objects in new images. This training is usually computationally intensive, consists of thousands of epochs, and can take tens of hours for each target object. Even after the model training in completed, there is still a chance of failure if the real-time tracking and object detection phases lack sufficient accuracy, precision, and/or speed for many important applications. Here we present a system and approach which minimizes the computational expense of the various steps in the training and real-time tracking process outlined above of for applications in the development of mixed-reality science laboratory experiences by using non-intrusive object-encoding 2D QR codes that are mounted directly onto the surfaces of the lab tools to be tracked. This system can start detecting and tracking it immediately and eliminates the laborious process of acquiring and annotating a new training dataset for every new lab tool to be tracked.more » « less
-
Abstract Insect pests cause significant damage to food production, so early detection and efficient mitigation strategies are crucial. There is a continual shift toward machine learning (ML)‐based approaches for automating agricultural pest detection. Although supervised learning has achieved remarkable progress in this regard, it is impeded by the need for significant expert involvement in labeling the data used for model training. This makes real‐world applications tedious and oftentimes infeasible. Recently, self‐supervised learning (SSL) approaches have provided a viable alternative to training ML models with minimal annotations. Here, we present an SSL approach to classify 22 insect pests. The framework was assessed on raw and segmented field‐captured images using three different SSL methods, Nearest Neighbor Contrastive Learning of Visual Representations (NNCLR), Bootstrap Your Own Latent, and Barlow Twins. SSL pre‐training was done on ResNet‐18 and ResNet‐50 models using all three SSL methods on the original RGB images and foreground segmented images. The performance of SSL pre‐training methods was evaluated using linear probing of SSL representations and end‐to‐end fine‐tuning approaches. The SSL‐pre‐trained convolutional neural network models were able to perform annotation‐efficient classification. NNCLR was the best performing SSL method for both linear and full model fine‐tuning. With just 5% annotated images, transfer learning with ImageNet initialization obtained 74% accuracy, whereas NNCLR achieved an improved classification accuracy of 79% for end‐to‐end fine‐tuning. Models created using SSL pre‐training consistently performed better, especially under very low annotation, and were robust to object class imbalances. These approaches help overcome annotation bottlenecks and are resource efficient.more » « less
-
Visual event perception tasks such as action localization have primarily focused on supervised learning settings under a static observer, i.e., the camera is static and cannot be controlled by an algorithm. They are often restricted by the quality, quantity, and diversity of annotated training data and do not often generalize to out-of-domain samples. In this work, we tackle the problem of active action localization where the goal is to localize an action while controlling the geometric and physical parameters of an active camera to keep the action in the field of view without training data. We formulate an energy-based mechanism that combines predictive learning and reactive control to perform active action localization without rewards, which can be sparse or non-existent in real-world environments. We perform extensive experiments in both simulated and real-world environments on two tasks - active object tracking and active action localization. We demonstrate that the proposed approach can generalize to different tasks and environments in a streaming fashion, without explicit rewards or training. We show that the proposed approach outperforms unsupervised baselines and obtains competitive performance compared to those trained with reinforcement learning.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1145/3576842.3582366
