When robots entered our day-to-day life, the shared space surrounding humans and robots is critical for effective Human-Robot collaboration. The design of shared space should satisfy humans' preferences and robots' efficiency. This work uses kitchen design as an example to illustrate the importance of good space design in facilitating such collaboration. Given the kitchen boundary, counters, and recipes, the proposed method computes the optimal placement of counters that meet the requirement of kitchen design rules and improve Human-Robot collaboration. The key technical challenge is that the optimization method usually evaluates thousands of designs and the computational cost of motion planning, which is part of the evaluation function, is expensive. We use a decentralized motion planner that can solve multi-agent motion planning efficiently. Our results indicate that optimized kitchen designs can provide noticeable performance improvement to Human-Robot collaboration.

Evaluating the worst-case performance of a reinforcement learning (RL) agent under the strongest/optimal adversarial perturbations on state observations (within some constraints) is crucial for understanding the robustness of RL agents. However, finding the optimal adversary is challenging, in terms of both whether we can find the optimal attack and how efficiently we can find it. Existing works on adversarial RL either use heuristics-based methods that may not find the strongest adversary, or directly train an RL-based adversary by treating the agent as a part of the environment, which can find the optimal adversary but may become intractable in a large state space. This paper introduces a novel attacking method to find the optimal attacks through collaboration between a designed function named "actor" and an RL-based learner named "director". The actor crafts state perturbations for a given policy perturbation direction, and the director learns to propose the best policy perturbation directions. Our proposed algorithm, PA-AD, is theoretically optimal and significantly more efficient than prior RL-based works in environments with large state spaces. Empirical results show that our proposed PA-AD universally outperforms state-of-the-art attacking methods in various Atari and MuJoCo environments. By applying PA-AD to adversarial training, we achieve state-of-the-art empirical robustness in multiple tasks under strong adversaries. The codebase is released at https://github.com/umd-huang-lab/paad_adv_rl.

This paper addresses learning end-to-end models for time series data that include a temporal alignment step via dynamic time warping (DTW). Existing approaches to differentiable DTW either differentiate through a fixed warping path or apply a differentiable relaxation to the min operator found in the recursive steps used to solve the DTW problem. We instead propose a DTW layer based around bi-level optimisation and deep declarative networks, which we name DecDTW. By formulating DTW as a continuous, inequality constrained optimisation problem, we can compute gradients for the solution of the optimal alignment (with respect to the underlying time series) using implicit differentiation. An interesting byproduct of this formulation is that DecDTW outputs the optimal warping path between two time series as opposed to a soft approximation, recoverable from Soft-DTW. We show that this property is particularly useful for applications where downstream loss functions are defined on the optimal alignment path itself. This naturally occurs, for instance, when learning to improve the accuracy of predicted alignments against ground truth alignments. We evaluate DecDTW on two such applications, namely the audio-to-score alignment task in music information retrieval and the visual place recognition task in robotics, demonstrating state-of-the-art results in both.

This paper presents an efficient approach to object manipulation planning using Monte Carlo Tree Search (MCTS) to find contact sequences and an efficient ADMM-based trajectory optimization algorithm to evaluate the dynamic feasibility of candidate contact sequences. To accelerate MCTS, we propose a methodology to learn a goal-conditioned policy-value network to direct the search towards promising nodes. Further, manipulation-specific heuristics enable to drastically reduce the search space. Systematic object manipulation experiments in a physics simulator and on real hardware demonstrate the efficiency of our approach. In particular, our approach scales favorably for long manipulation sequences thanks to the learned policy-value network, significantly improving planning success rate.

We propose a robust framework for the planar pose graph optimization contaminated by loop closure outliers. Our framework rejects outliers by first decoupling the robust PGO problem wrapped by a Truncated Least Squares kernel into two subproblems. Then, the framework introduces a linear angle representation to rewrite the first subproblem that is originally formulated with rotation matrices. The framework is configured with the Graduated Non-Convexity (GNC) algorithm to solve the two non-convex subproblems in succession without initial guesses. Thanks to the linearity properties of both the subproblems, our framework requires only linear solvers to optimally solve the optimization problems encountered in GNC. We extensively validate the proposed framework, named DEGNC-LAF (DEcoupled Graduated Non-Convexity with Linear Angle Formulation) in planar PGO benchmarks. It turns out that it runs significantly (sometimes up to over 30 times) faster than the standard and general-purpose GNC while resulting in high-quality estimates.

Value iteration can find the optimal replenishment policy for a perishable inventory problem, but is computationally demanding due to the large state spaces that are required to represent the age profile of stock. The parallel processing capabilities of modern GPUs can reduce the wall time required to run value iteration by updating many states simultaneously. The adoption of GPU-accelerated approaches has been limited in operational research relative to other fields like machine learning, in which new software frameworks have made GPU programming widely accessible. We used the Python library JAX to implement value iteration and simulators of the underlying Markov decision processes in a high-level API, and relied on this library's function transformations and compiler to efficiently utilize GPU hardware. Our method can extend use of value iteration to settings that were previously considered infeasible or impractical. We demonstrate this on example scenarios from three recent studies which include problems with over 16 million states and additional problem features, such as substitution between products, that increase computational complexity. We compare the performance of the optimal replenishment policies to heuristic policies, fitted using simulation optimization in JAX which allowed the parallel evaluation of multiple candidate policy parameters on thousands of simulated years. The heuristic policies gave a maximum optimality gap of 2.49%. Our general approach may be applicable to a wide range of problems in operational research that would benefit from large-scale parallel computation on consumer-grade GPU hardware.

Protein sequence design is a challenging problem in protein engineering, which aims to discover novel proteins with useful biological functions. Directed evolution is a widely-used approach for protein sequence design, which mimics the evolution cycle in a laboratory environment and conducts an iterative protocol. However, the burden of laboratory experiments can be reduced by using machine learning approaches to build a surrogate model of the protein landscape and conducting in-silico population selection through model-based fitness prediction. In this paper, we propose a new method based on Batch Bayesian Optimization (Batch BO), a well-established optimization method, for protein sequence design. By incorporating Batch BO into the directed evolution process, our method is able to make more informed decisions about which sequences to select for artificial evolution, leading to improved performance and faster convergence. We evaluate our method on a suite of in-silico protein sequence design tasks and demonstrate substantial improvement over baseline algorithms.

Trajectory optimization has been used extensively in robotic systems. In particular, iterative Linear Quadratic Regulator (iLQR) has performed well as an off-line planner and online nonlinear model predictive control solver, with a lower computational cost. However, standard iLQR cannot handle any constraints or perform reasonable initialization of a state trajectory. In this paper, we propose a hybrid constrained iLQR variant with a multiple-shooting framework to incorporate general inequality constraints and infeasible states initialization. The main technical contributions are twofold: 1) In addition to inheriting the simplicity of the initialization in multiple-shooting settings, a two-stage framework is developed to deal with state and/or control constraints robustly without loss of the linear feedback term of iLQR. Such a hybrid strategy offers fast convergence of constraint satisfaction. 2) An improved globalization strategy is proposed to exploit the coupled effects between line-searching and regularization, which is able to enhance the numerical robustness of the constrained iLQR approaches. Our approach is tested on various constrained trajectory optimization problems and outperforms the commonly-used collocation and shooting methods.

The existing intelligent optimization algorithms are designed based on the finest granularity, i.e., a point. This leads to weak global search ability and inefficiency. To address this problem, we proposed a novel multi-granularity optimization algorithm, namely granular-ball optimization algorithm (GBO), by introducing granular-ball computing. GBO uses many granular-balls to cover the solution space. Quite a lot of small and fine-grained granular-balls are used to depict the important parts, and a little number of large and coarse-grained granular-balls are used to depict the inessential parts. Fine multi-granularity data description ability results in a higher global search capability and faster convergence speed. In comparison with the most popular and state-of-the-art algorithms, the experiments on twenty benchmark functions demonstrate its better performance. The faster speed, higher approximation ability of optimal solution, no hyper-parameters, and simpler design of GBO make it an all-around replacement of most of the existing popular intelligent optimization algorithms.

Data-driven algorithms are only as good as the data they work with, while data sets, especially social data, often fail to represent minorities adequately. Representation Bias in data can happen due to various reasons ranging from historical discrimination to selection and sampling biases in the data acquisition and preparation methods. Given that "bias in, bias out", one cannot expect AI-based solutions to have equitable outcomes for societal applications, without addressing issues such as representation bias. While there has been extensive study of fairness in machine learning models, including several review papers, bias in the data has been less studied. This paper reviews the literature on identifying and resolving representation bias as a feature of a data set, independent of how consumed later. The scope of this survey is bounded to structured (tabular) and unstructured (e.g., image, text, graph) data. It presents taxonomies to categorize the studied techniques based on multiple design dimensions and provides a side-by-side comparison of their properties. There is still a long way to fully address representation bias issues in data. The authors hope that this survey motivates researchers to approach these challenges in the future by observing existing work within their respective domains.