While humans can use parts of their arms other than the hands for manipulations like gathering and supporting, whether robots can effectively learn and perform the same type of operations remains relatively unexplored. As these manipulations require joint-level control to regulate the complete poses of the robots, we develop AirExo, a low-cost, adaptable, and portable dual-arm exoskeleton, for teleoperation and demonstration collection. As collecting teleoperated data is expensive and time-consuming, we further leverage AirExo to collect cheap in-the-wild demonstrations at scale. Under our in-the-wild learning framework, we show that with only 3 minutes of the teleoperated demonstrations, augmented by diverse and extensive in-the-wild data collected by AirExo, robots can learn a policy that is comparable to or even better than one learned from teleoperated demonstrations lasting over 20 minutes. Experiments demonstrate that our approach enables the model to learn a more general and robust policy across the various stages of the task, enhancing the success rates in task completion even with the presence of disturbances. Project website: airexo.github.io.

Reactive grasping, which enables the robot to successfully grasp dynamic moving objects, is of great interest in robotics. Current methods mainly focus on the temporal smoothness of the predicted grasp poses but few consider their semantic consistency. Consequently, the predicted grasps are not guaranteed to fall on the same part of the same object, especially in cluttered scenes. In this paper, we propose to solve reactive grasping in a target-referenced setting by tracking through generated grasp spaces. Given a targeted grasp pose on an object and detected grasp poses in a new observation, our method is composed of two stages: 1) discovering grasp pose correspondences through an attentional graph neural network and selecting the one with the highest similarity with respect to the target pose; 2) refining the selected grasp poses based on target and historical information. We evaluate our method on a large-scale benchmark GraspNet-1Billion. We also collect 30 scenes of dynamic objects for testing. The results suggest that our method outperforms other representative methods. Furthermore, our real robot experiments achieve an average success rate of over 80 percent. Code and demos are available at: https://graspnet.net/reactive.

In this work we present several methods for fast integer motion estimation of videos recorded aboard an Unmanned Aerial Vehicle (UAV). Different from related work, the field depth is not considered to be consistent. The novel methods designed for low complexity MV prediction in H.264/AVC and analysis hereof include histogram-based prediction, constant global motion, and modification of the candidate sets in the Enhanced Predictive Zonal Search (EPZS). The results verify the applicability of the methods with a speed-up factor of integer motion estimation up to 2-4. Initial results for UAV infrared (IR) video are also provided.

Since the first shape-from-shading (SFS) technique was developed by Horn in the early 1970s, many different approaches have emerged. In this paper, six well-known SFS algorithms are implemented and compared. The performance of the algorithms was analyzed on synthetic images using mean and standard deviation of depth (Z) error, mean of surface gradient (p, q) error, and CPU timing. Each algorithm works well for certain images, but performs poorly for others. In general, minimization approaches are more robust, while the other approaches are faster.

We propose a new shape-from-shading (SFS) algorithm which replaces the brightness constraint with an intensity gradient constraint. This is a global approach which obtains the solution by the minimization of an error function over the entire image. Through the linearization of the gradient of the reflectance map and the discretization of the surface gradient, the intensity gradient can be expressed as a linear function of the surface height. A quadratic error function, which involves the intensity gradient constraint and the traditional smoothness constraint, is minimized efficiently by solving a sparse linear system using the multigrid technique. Neither the information at singular points nor the information at occluding boundaries is needed for the initialization of the height. Results for real images are presented to show the robustness of the algorithm, and the execution time is demonstrated to prove its efficiency.

Unlike existing global shape-from-shading algorithms which involve the brightness constraint in their formulation, we propose a new algorithm which replaces the brightness constraint by an intensity gradient constraint. This is a global approach which obtains the solution by the minimization of an error function over the entire image. Through the linearization of the reflectance map and the discretization of the surface gradient, the intensity gradient can be expressed as a linear function of the surface height. A quadratic error function, which involves the intensity gradient constraint and the traditional smoothness constraint, is minimized efficiently by solving a sparse linear system using the multigrid technique. Neither the information at singular points nor the information at occluding boundaries is needed for the initialization.>

Since the first shape-from-shading technique was developed by B.K.P. Horn in the early 1970s, different approaches have been continuously emerging in the past two decades. Some of them, improve existing techniques, while others are completely new approaches. However, there is no literature on, the comparison and performance analysis of these techniques. This paper provides comparison and analysis of these techniques.>

A new technique called shape from photomotion is introduced. It uses a series of 2-D Lambertian images, generated by moving a light source around a scene, to recover the depth map. In each of the images, the object in the scene remains at a fixed position and the only variable is the light source direction. The movement of the light source causes a change in the intensity of any given point in the image. The change in intensity is what enables recovery of the unknown parameter, the depth map, since it remains constant in each of the input images. The authors' method differs from photometric stereo in the sense that the shape estimate is not only computed for each light source orientation, but also gradually refined by photomotion.>