Machine learning models of visual action recognition are typically trained and tested on data from specific situations where actions are associated with certain objects. It is an open question how action-object associations in the training set influence a model's ability to generalize beyond trained situations. We set out to identify properties of training data that lead to action recognition models with greater generalization ability. To do this, we take inspiration from a cognitive mechanism called cross-situational learning, which states that human learners extract the meaning of concepts by observing instances of the same concept across different situations. We perform controlled experiments with various types of action-object associations, and identify key properties of action-object co-occurrence in training data that lead to better classifiers. Given that these properties are missing in the datasets that are typically used to train action classifiers in the computer vision literature, our work provides useful insights on how we should best construct datasets for efficiently training for better generalization.
This paper presents the design, analysis, and performance evaluation of an omnidirectional transformable wheel-leg robot called OmniWheg. We design a novel mechanism consisting of a separable Omni-wheel and 4-bar linkages, allowing the robot to transform between Omni-wheeled and legged modes smoothly. On wheeled mode, the robot can move in all directions and efficiently adjust the relative position of its wheels, while it can overcome common obstacles in legged mode, such as stairs and steps. Unlike other articles studying whegs, this implementation with omnidirectional wheels allows the correction of misalignments between right and left wheels before traversing obstacles, which effectively improves the success rate and simplifies the preparation process before the wheel-leg transformation. We describe the design concept, mechanism, and the dynamic characteristic of the wheel-leg structure. We then evaluate its performance in various scenarios, including passing obstacles, climbing steps of different heights, and turning/moving omnidirectionally. Our results confirm that this mobile platform can overcome common indoor obstacles and move flexibly on the flat ground with the new transformable wheel-leg mechanism, while keeping a high degree of stability.
While quadruped robots usually have good stability and load capacity, bipedal robots offer a higher level of flexibility / adaptability to different tasks and environments. A multi-modal legged robot can take the best of both worlds. In this paper, we propose a multi-modal locomotion framework that is composed of a hand-crafted transition motion and a learning-based bipedal controller -- learnt by a novel algorithm called Automated Residual Reinforcement Learning. This framework aims to endow arbitrary quadruped robots with the ability to walk bipedally. In particular, we 1) design an additional supporting structure for a quadruped robot and a sequential multi-modal transition strategy; 2) propose a novel class of Reinforcement Learning algorithms for bipedal control and evaluate their performances in both simulation and the real world. Experimental results show that our proposed algorithms have the best performance in simulation and maintain a good performance in a real-world robot. Overall, our multi-modal robot could successfully switch between biped and quadruped, and walk in both modes. Experiment videos and code are available at https://chenaah.github.io/multimodal/.
Nowadays many cities around the world have introduced electric buses to optimize urban traffic and reduce local carbon emissions. In order to cut carbon emissions and maximize the utility of electric buses, it is important to choose suitable routes for them. Traditionally, route selection is on the basis of dedicated surveys, which are costly in time and labor. In this paper, we mainly focus attention on planning electric bus routes intelligently, depending on the unique needs of each region throughout the city. We propose Clairvoyance, a route planning system that leverages a deep neural network and a multilayer perceptron to predict the future people's trips and the future transportation carbon emission in the whole city, respectively. Given the future information of people's trips and transportation carbon emission, we utilize a greedy mechanism to recommend bus routes for electric buses that will depart in an ideal state. Furthermore, representative features of the two neural networks are extracted from the heterogeneous urban datasets. We evaluate our approach through extensive experiments on real-world data sources in Zhuhai, China. The results show that our designed neural network-based algorithms are consistently superior to the typical baselines. Additionally, the recommended routes for electric buses are helpful in reducing the peak value of carbon emissions and making full use of electric buses in the city.
Robots with the ability to actively acquire power from surroundings will be greatly beneficial for long-term autonomy and to survive in uncertain environments. In this work, we present a robot capable of drawing circuits with conductive ink while also rearranging the visual world to receive maximum energy from a power source. A range of circuit drawing tasks is designed to simulate real-world scenarios, including avoiding physical obstacles and regions that would discontinue drawn circuits. We adopt the state-of-the-art Transporter networks for pick-and-place manipulation from visual observation. We conduct experiments in both simulation and real-world settings, and our results show that, with a small number of demonstrations, the robot learns to rearrange the placement of objects (removing obstacles and bridging areas unsuitable for drawing) and to connect a power source with a minimum amount of conductive ink. As autonomous robots become more present, in our houses and other planets, our proposed method brings a novel way for machines to keep themselves functional by rearranging their surroundings to create their own electric circuits.
We present the visually-grounded language modelling track that was introduced in the Zero-Resource Speech challenge, 2021 edition, 2nd round. We motivate the new track and discuss participation rules in detail. We also present the two baseline systems that were developed for this track.
We analyze egocentric views of attended objects from infants. This paper shows 1) empirical evidence that children's egocentric views have more diverse distributions compared to adults' views, 2) we can computationally simulate the infants' distribution, and 3) the distribution is beneficial for training more generalized image classifiers not only for infant egocentric vision but for third-person computer vision.
For many data mining and machine learning tasks, the quality of a similarity measure is the key for their performance. To automatically find a good similarity measure from datasets, metric learning and similarity learning are proposed and studied extensively. Metric learning will learn a Mahalanobis distance based on positive semi-definite (PSD) matrix, to measure the distances between objectives, while similarity learning aims to directly learn a similarity function without PSD constraint so that it is more attractive. Most of the existing similarity learning algorithms are online similarity learning method, since online learning is more scalable than offline learning. However, most existing online similarity learning algorithms learn a full matrix with d 2 parameters, where d is the dimension of the instances. This is clearly inefficient for high dimensional tasks due to its high memory and computational complexity. To solve this issue, we introduce several Sparse Online Relative Similarity (SORS) learning algorithms, which learn a sparse model during the learning process, so that the memory and computational cost can be significantly reduced. We theoretically analyze the proposed algorithms, and evaluate them on some real-world high dimensional datasets. Encouraging empirical results demonstrate the advantages of our approach in terms of efficiency and efficacy.
Human infants have the remarkable ability to learn the associations between object names and visual objects from inherently ambiguous experiences. Researchers in cognitive science and developmental psychology have built formal models that implement in-principle learning algorithms, and then used pre-selected and pre-cleaned datasets to test the abilities of the models to find statistical regularities in the input data. In contrast to previous modeling approaches, the present study used egocentric video and gaze data collected from infant learners during natural toy play with their parents. This allowed us to capture the learning environment from the perspective of the learner's own point of view. We then used a Convolutional Neural Network (CNN) model to process sensory data from the infant's point of view and learn name-object associations from scratch. As the first model that takes raw egocentric video to simulate infant word learning, the present study provides a proof of principle that the problem of early word learning can be solved, using actual visual data perceived by infant learners. Moreover, we conducted simulation experiments to systematically determine how visual, perceptual, and attentional properties of infants' sensory experiences may affect word learning.
Due to the foveated nature of the human vision system, people can focus their visual attention on a small region of their visual field at a time, which usually contains only a single object. Estimating this object of attention in first-person (egocentric) videos is useful for many human-centered real-world applications such as augmented reality applications and driver assistance systems. A straightforward solution for this problem is to pick the object whose bounding box is hit by the gaze, where eye gaze point estimation is obtained from a traditional eye gaze estimator and object candidates are generated from an off-the-shelf object detector. However, such an approach can fail because it addresses the where and the what problems separately, despite that they are highly related, chicken-and-egg problems. In this paper, we propose a novel unified model that incorporates both spatial and temporal evidence in identifying as well as locating the attended object in firstperson videos. It introduces a novel Self Validation Module that enforces and leverages consistency of the where and the what concepts. We evaluate on two public datasets, demonstrating that Self Validation Module significantly benefits both training and testing and that our model outperforms the state-of-the-art.