Robot control for tactile feedback-based manipulation can be difficult due to the modeling of physical contacts, partial observability of the environment, and noise in perception and control. This work focuses on solving partial observability of contact-rich manipulation tasks as a Sequence-to-Sequence (Seq2Seq)} Imitation Learning (IL) problem. The proposed Seq2Seq model produces a robot-environment interaction sequence to estimate the partially observable environment state variables. Then, the observed interaction sequence is transformed to a control sequence for the task itself. The proposed Seq2Seq IL for tactile feedback-based manipulation is experimentally validated on a door-open task in a simulated environment and a snap-on insertion task with a real robot. The model is able to learn both tasks from only 50 expert demonstrations, while state-of-the-art reinforcement learning and imitation learning methods fail.

Recent works have shown that deep learning (DL) models can effectively learn city-wide crowd-flow patterns, which can be used for more effective urban planning and smart city management. However, DL models have been known to perform poorly on inconspicuous adversarial perturbations. Although many works have studied these adversarial perturbations in general, the adversarial vulnerabilities of deep crowd-flow prediction models in particular have remained largely unexplored. In this paper, we perform a rigorous analysis of the adversarial vulnerabilities of DL-based crowd-flow prediction models under multiple threat settings, making three-fold contributions. (1) We propose CaV-detect by formally identifying two novel properties - Consistency and Validity - of the crowd-flow prediction inputs that enable the detection of standard adversarial inputs with 0% false acceptance rate (FAR). (2) We leverage universal adversarial perturbations and an adaptive adversarial loss to present adaptive adversarial attacks to evade CaV-detect defense. (3) We propose CVPR, a Consistent, Valid and Physically-Realizable adversarial attack, that explicitly inducts the consistency and validity priors in the perturbation generation mechanism. We find out that although the crowd-flow models are vulnerable to adversarial perturbations, it is extremely challenging to simulate these perturbations in physical settings, notably when CaV-detect is in place. We also show that CVPR attack considerably outperforms the adaptively modified standard attacks in FAR and adversarial loss metrics. We conclude with useful insights emerging from our work and highlight promising future research directions.

Cooperative multi-agent policy gradient (MAPG) algorithms have recently attracted wide attention and are regarded as a general scheme for the multi-agent system. Credit assignment plays an important role in MAPG and can induce cooperation among multiple agents. However, most MAPG algorithms cannot achieve good credit assignment because of the game-theoretic pathology known as \textit{centralized-decentralized mismatch}. To address this issue, this paper presents a novel method, \textit{\underline{M}ulti-\underline{A}gent \underline{P}olarization \underline{P}olicy \underline{G}radient} (MAPPG). MAPPG takes a simple but efficient polarization function to transform the optimal consistency of joint and individual actions into easily realized constraints, thus enabling efficient credit assignment in MAPG. Theoretically, we prove that individual policies of MAPPG can converge to the global optimum. Empirically, we evaluate MAPPG on the well-known matrix game and differential game, and verify that MAPPG can converge to the global optimum for both discrete and continuous action spaces. We also evaluate MAPPG on a set of StarCraft II micromanagement tasks and demonstrate that MAPPG outperforms the state-of-the-art MAPG algorithms.

Artificial intelligence (AI) has a history of nearly a century from its inception to the present day. We have summarized the development trends and discovered universal rules, including both success and failure. We have analyzed the reasons from both technical and philosophical perspectives to help understand the reasons behind the past failures and current successes of AI, and to provide a basis for thinking and exploring future development. Specifically, we have found that the development of AI in different fields, including computer vision, natural language processing, and machine learning, follows a pattern from rules to statistics to data-driven methods. In the face of past failures and current successes, we need to think systematically about the reasons behind them. Given the unity of AI between natural and social sciences, it is necessary to incorporate philosophical thinking to understand and solve AI problems, and we believe that starting from the dialectical method of Marx is a feasible path. We have concluded that the sustainable development direction of AI should be human-machine collaboration and a technology path centered on computing power. Finally, we have summarized the impact of AI on society from this trend.

In recent years, Reinforcement Learning (RL) has been applied to real-world problems with increasing success. Such applications often require to put constraints on the agent's behavior. Existing algorithms for constrained RL (CRL) rely on gradient descent-ascent, but this approach comes with a caveat. While these algorithms are guaranteed to converge on average, they do not guarantee last-iterate convergence, i.e., the current policy of the agent may never converge to the optimal solution. In practice, it is often observed that the policy alternates between satisfying the constraints and maximizing the reward, rarely accomplishing both objectives simultaneously. Here, we address this problem by introducing Reinforcement Learning with Optimistic Ascent-Descent (ReLOAD), a principled CRL method with guaranteed last-iterate convergence. We demonstrate its empirical effectiveness on a wide variety of CRL problems including discrete MDPs and continuous control. In the process we establish a benchmark of challenging CRL problems.

Energy-based models parameterize the unnormalized log-probability of data samples, but there is a lack of guidance on how to construct the "energy". In this paper, we propose a Denoising-EBM which decomposes the image energy into "semantic energy" and "texture energy". We define the "semantic energy" in the latent space of DAE to model the high-level representations, and define the pixel-level reconstruction error for denoising as "texture energy". Inspired by score-based model, our model utilizes multi-scale noisy samples for maximum-likelihood training and it outputs a vector instead of a scalar for exploring a larger set of functions during optimization. After training, the semantics are first synthesized by fast MCMC through "semantic energy", and then the pixel-level refinement of semantic image will be performed to generate perfect samples based on "texture energy". Ultimately, our model can outperform most EBMs in image generation. And we also demonstrate that Denoising-EBM has top performance among EBMs for out-of-distribution detection.

Legged robot navigation in unstructured and slippery terrains depends heavily on the ability to accurately identify the quality of contact between the robot's feet and the ground. Contact state estimation is regarded as a challenging problem and is typically addressed by exploiting force measurements, joint encoders and/or robot kinematics and dynamics. In contrast to most state of the art approaches, the current work introduces a novel probabilistic method for estimating the contact state based solely on proprioceptive sensing, as it is readily available by Inertial Measurement Units (IMUs) mounted on the robot's end effectors. Capitalizing on the uncertainty of IMU measurements, our method estimates the probability of stable contact. This is accomplished by approximating the multimodal probability density function over a batch of data points for each axis of the IMU with Kernel Density Estimation. The proposed method has been extensively assessed against both real and simulated scenarios on bipedal and quadrupedal robotic platforms such as ATLAS, TALOS and Unitree's GO1.

Effective traffic control methods have great potential in alleviating network congestion. Existing literature generally focuses on a single control approach, while few studies have explored the effectiveness of integrated and coordinated control approaches. This study considers two representative control approaches: ramp metering for freeways and perimeter control for homogeneous urban roads, and we aim to develop a deep reinforcement learning (DRL)-based coordinated control framework for large-scale networks. The main challenges are 1) there is a lack of efficient dynamic models for both freeways and urban roads; 2) the standard DRL method becomes ineffective due to the complex and non-stationary network dynamics. In view of this, we propose a novel meso-macro dynamic network model and first time develop a demonstration-guided DRL method to achieve large-scale coordinated ramp metering and perimeter control. The dynamic network model hybridizes the link and generalized bathtub models to depict the traffic dynamics of freeways and urban roads, respectively. For the DRL method, we incorporate demonstration to guide the DRL method for better convergence by introducing the concept of "teacher" and "student" models. The teacher models are traditional controllers (e.g., ALINEA, Gating), which provide control demonstrations. The student models are DRL methods, which learn from the teacher and aim to surpass the teacher's performance. To validate the proposed framework, we conduct two case studies in a small-scale network and a real-world large-scale traffic network in Hong Kong. The research outcome reveals the great potential of combining traditional controllers with DRL for coordinated control in large-scale networks.

Quantum Bayesian Computation (QBC) is an emerging field that levers the computational gains available from quantum computers to provide an exponential speed-up in Bayesian computation. Our paper adds to the literature in two ways. First, we show how von Neumann quantum measurement can be used to simulate machine learning algorithms such as Markov chain Monte Carlo (MCMC) and Deep Learning (DL) that are fundamental to Bayesian learning. Second, we describe data encoding methods needed to implement quantum machine learning including the counterparts to traditional feature extraction and kernel embeddings methods. Our goal then is to show how to apply quantum algorithms directly to statistical machine learning problems. On the theoretical side, we provide quantum versions of high dimensional regression, Gaussian processes (Q-GP) and stochastic gradient descent (Q-SGD). On the empirical side, we apply a Quantum FFT model to Chicago housing data. Finally, we conclude with directions for future research.

Over the last two decades, the robotics community witnessed the emergence of various motion representations that have been used extensively, particularly in behavorial cloning, to compactly encode and generalize skills. Among these, probabilistic approaches have earned a relevant place, owing to their encoding of variations, correlations and adaptability to new task conditions. Modulating such primitives, however, is often cumbersome due to the need for parameter re-optimization which frequently entails computationally costly operations. In this paper we derive a non-parametric movement primitive formulation that contains a null space projector. We show that such formulation allows for fast and efficient motion generation with computational complexity O(n2) without involving matrix inversions, whose complexity is O(n3). This is achieved by using the null space to track secondary targets, with a precision determined by the training dataset. Using a 2D example associated with time input we show that our non-parametric solution compares favourably with a state-of-the-art parametric approach. For demonstrated skills with high-dimensional inputs we show that it permits on-the-fly adaptation as well.