Mechatronics, a multidisciplinary field and transformed the conventional methods to dynamic and autonomous systems. The emergence of robotics and technology in various sectors marks a significant revolution in the ind...
详细信息
Bipedal robots are inherently poorly self-stabilizing mechanisms. To enhance stability and achieve high-level dynamic control, it is necessary to refine the mechanism design, which often leads to an increase in degree...
详细信息
This paper studies the adaptive fault-tolerant control problem for switched nonlinear systems with full-state constraints and unknown functions. To address this challenge, radial basis function neural networks (RBFNNs...
详细信息
Applying reinforcement learning (RL) methods on robots typically involves training a policy in simulation and deploying it on a robot in the real world. Because of the model mismatch between the real world and the sim...
详细信息
ISBN:
(纸本)9781728196817
Applying reinforcement learning (RL) methods on robots typically involves training a policy in simulation and deploying it on a robot in the real world. Because of the model mismatch between the real world and the simulator, RL agents deployed in this manner tend to perform suboptimally. To tackle this problem, researchers have developed robust policy learning algorithms that rely on synthetic noise disturbances. However, such methods do not guarantee performance in the target environment. We propose a convex risk minimization algorithm to estimate the model mismatch between the simulator and the target domain using trajectory data from both environments. We show that this estimator can be used along with the simulator to evaluate performance of an RL agents in the target domain, effectively bridging the gap between these two environments. We also show that the convergence rate of our estimator to be of the order of n, where n is the number of training samples. In simulation, we demonstrate how our method effectively approximates and evaluates performance on Gridworld, Cartpole, and Reacher environments on a range of policies. We also show that the our method is able to estimate performance of a 7 DOF robotic arm using the simulator and remotely collected data from the robot in the real world.
Visual servoing enables robotic systems to perform accurate closed-loop control, which is required in many applications. However, existing methods require either precise calibration of the robot kinematic model and ca...
详细信息
ISBN:
(纸本)9781728196817
Visual servoing enables robotic systems to perform accurate closed-loop control, which is required in many applications. However, existing methods require either precise calibration of the robot kinematic model and cameras or use neural architectures that require large amounts of data to train. In this work, we present a method for unsupervised learning of visual servoing that does not require any prior calibration and is extremely data-efficient. Our key insight is that visual servoing does not depend on identifying the veridical kinematic and camera parameters, but instead only on an accurate generative model of image feature observations from the joint positions of the robot. We demonstrate that with our model architecture and learning algorithm, we can consistently learn accurate models from less than 50 training samples (which amounts to less than 1 min of unsupervised data collection), and that such data-efficient learning is not possible with standard neural architectures. Further, we show that by using the generative model in the loop and learning online, we can enable a robotic system to recover from calibration errors and to detect and quickly adapt to possibly unexpected changes in the robot-camera system (e.g. bumped camera, new objects).
This paper presents a novel cable-driven 7-degree-of-freedom redundant anthropomorphic manipulator designed to address the challenge of adjustable stiffness in robotic arms. By exploiting the inherent properties of ca...
详细信息
Predicting future trajectories of road agents is a critical task for autonomous driving. Recent goal-based trajectory prediction methods, such as DenseTNT and PECNet [1, 2], have shown good performance on prediction t...
详细信息
ISBN:
(纸本)9781728196817
Predicting future trajectories of road agents is a critical task for autonomous driving. Recent goal-based trajectory prediction methods, such as DenseTNT and PECNet [1, 2], have shown good performance on prediction tasks on public datasets. However, they usually require complicated goal-selection algorithms and optimization. In this work, we propose KEMP, a hierarchical end-to-end deep learning framework for trajectory prediction. At the core of our framework is keyframe-based trajectory prediction, where keyframes are representative states that trace out the general direction of the trajectory. KEMP first predicts keyframes conditioned on the road context, and then fills in intermediate states conditioned on the keyframes and the road context. Under our general framework, goal-conditioned methods are special cases in which the number of keyframes equal to one. Unlike goal-conditioned methods, our keyframe predictor is learned automatically and does not require hand-crafted goal-selection algorithms. We evaluate our model on public benchmarks and our model ranked 1st on Waymo Open Motion Dataset Leaderboard (as of September 1, 2021).
This survey paper offers a comprehensive analysis of recent advancements in eXplainable Artificial Intelligence (XAI) for data analytics, drawing from a meticulous review of 31 pertinent papers. Leveraging a focused s...
详细信息
While modern deep neural networks are performant perception modules, performance (accuracy) alone is insufficient, particularly for safety-critical robotic applications such as self-driving vehicles. Robot autonomy st...
详细信息
ISBN:
(纸本)9781728196817
While modern deep neural networks are performant perception modules, performance (accuracy) alone is insufficient, particularly for safety-critical robotic applications such as self-driving vehicles. Robot autonomy stacks also require these otherwise blackbox models to produce reliable and calibrated measures of confidence on their predictions. Existing approaches estimate uncertainty from these neural network perception stacks by modifying network architectures, inference procedure, or loss functions. However, in general, these methods lack calibration, meaning that the predictive uncertainties do not faithfully represent the true underlying uncertainties (process noise). Our key insight is that calibration is only achieved by imposing constraints across multiple examples, such as those in a mini-batch;as opposed to existing approaches which only impose constraints per-sample, often leading to overconfident (thus miscalibrated) uncertainty estimates. By enforcing the distribution of outputs of a neural network to resemble a target distribution by minimizing an f-divergence, we obtain significantly better-calibrated models compared to prior approaches. Our approach, f-Cal, outperforms existing uncertainty calibration approaches on robot perception tasks such as object detection and monocular depth estimation over multiple real-world benchmarks.
With the development of technology, there are more and more robots around us. These robots need to recognize human pose to monitor people or interact with people, so the human pose estimation model is required to be d...
详细信息
暂无评论