Recent advancements in meta-learning have enabled the automatic discovery of novel reinforcement learning algorithms parameterized by surrogate objective functions. To improve upon manually designed algorithms, the parameterization of this learned objective function must be expressive enough to represent novel principles of learning (instead of merely recovering already established ones) while still generalizing to a wide range of settings outside of its meta-training distribution. However, existing methods focus on discovering objective functions that, like many widely used objective functions in reinforcement learning, do not take into account the total number of steps allowed for training, or "training horizon". In contrast, humans use a plethora of different learning objectives across the course of acquiring a new ability. For instance, students may alter their studying techniques based on the proximity to exam deadlines and their self-assessed capabilities. This paper contends that ignoring the optimization time horizon significantly restricts the expressive potential of discovered learning algorithms. We propose a simple augmentation to two existing objective discovery approaches that allows the discovered algorithm to dynamically update its objective function throughout the agent's training procedure, resulting in expressive schedules and increased generalization across different training horizons. In the process, we find that commonly used meta-gradient approaches fail to discover such adaptive objective functions while evolution strategies discover highly dynamic learning rules. We demonstrate the effectiveness of our approach on a wide range of tasks and analyze the resulting learned algorithms, which we find effectively balance exploration and exploitation by modifying the structure of their learning rules throughout the agent's lifetime.
The integration of physiological computing into mixed-initiative human-robot interaction systems offers valuable advantages in autonomous task allocation by incorporating real-time features as human state observations into the decision-making system. This approach may alleviate the cognitive load on human operators by intelligently allocating mission tasks between agents. Nevertheless, accommodating a diverse pool of human participants with varying physiological and behavioral measurements presents a substantial challenge. To address this, resorting to a probabilistic framework becomes necessary, given the inherent uncertainty and partial observability on the human's state. Recent research suggests to learn a Partially Observable Markov Decision Process (POMDP) model from a data set of previously collected experiences that can be solved using Offline Reinforcement Learning (ORL) methods. In the present work, we not only highlight the potential of partially observable representations and physiological measurements to improve human operator state estimation and performance, but also enhance the overall mission effectiveness of a human-robot team. Importantly, as the fixed data set may not contain enough information to fully represent complex stochastic processes, we propose a method to incorporate model uncertainty, thus enabling risk-sensitive sequential decision-making. Experiments were conducted with a group of twenty-six human participants within a simulated robot teleoperation environment, yielding empirical evidence of the method's efficacy. The obtained adaptive task allocation policy led to statistically significant higher scores than the one that was used to collect the data set, allowing for generalization across diverse participants also taking into account risk-sensitive metrics.
Deep Neural Networks (DNNs) based semantic segmentation of the robotic instruments and tissues can enhance the precision of surgical activities in robot-assisted surgery. However, in biological learning, DNNs cannot learn incremental tasks over time and exhibit catastrophic forgetting, which refers to the sharp decline in performance on previously learned tasks after learning a new one. Specifically, when data scarcity is the issue, the model shows a rapid drop in performance on previously learned instruments after learning new data with new instruments. The problem becomes worse when it limits releasing the dataset of the old instruments for the old model due to privacy concerns and the unavailability of the data for the new or updated version of the instruments for the continual learning model. For this purpose, we develop a privacy-preserving synthetic continual semantic segmentation framework by blending and harmonizing (i) open-source old instruments foreground to the synthesized background without revealing real patient data in public and (ii) new instruments foreground to extensively augmented real background. To boost the balanced logit distillation from the old model to the continual learning model, we design overlapping class-aware temperature normalization (CAT) by controlling model learning utility. We also introduce multi-scale shifted-feature distillation (SD) to maintain long and short-range spatial relationships among the semantic objects where conventional short-range spatial features with limited information reduce the power of feature distillation. We demonstrate the effectiveness of our framework on the EndoVis 2017 and 2018 instrument segmentation dataset with a generalized continual learning setting. Code is available at~\url{https://github.com/XuMengyaAmy/Synthetic_CAT_SD}.
Robots must be able to understand their surroundings to perform complex tasks in challenging environments and many of these complex tasks require estimates of physical properties such as friction or weight. Estimating such properties using learning is challenging due to the large amounts of labelled data required for training and the difficulty of updating these learned models online at run time. To overcome these challenges, this paper introduces a novel, multi-modal approach for representing semantic predictions and physical property estimates jointly in a probabilistic manner. By using conjugate pairs, the proposed method enables closed-form Bayesian updates given visual and tactile measurements without requiring additional training data. The efficacy of the proposed algorithm is demonstrated through several hardware experiments. In particular, this paper illustrates that by conditioning semantic classifications on physical properties, the proposed method quantitatively outperforms state-of-the-art semantic classification methods that rely on vision alone. To further illustrate its utility, the proposed method is used in several applications including to represent affordance-based properties probabilistically and a challenging terrain traversal task using a legged robot. In the latter task, the proposed method represents the coefficient of friction of the terrain probabilistically, which enables the use of an on-line risk-aware planner that switches the legged robot from a dynamic gait to a static, stable gait when the expected value of the coefficient of friction falls below a given threshold. Videos of these case studies are presented in the multimedia attachment. The proposed framework includes an open-source C++ and ROS interface.
In robotics, contemporary strategies are learning-based, characterized by a complex black-box nature and a lack of interpretability, which may pose challenges in ensuring stability and safety. To address these issues, we propose integrating an obstacle-free deep reinforcement learning (DRL) trajectory planner with a novel auto-tuning low- and joint-level control strategy, all while actively engaging in the learning phase through interactions with the environment. This approach circumvents the complexities associated with computations while also addressing nonrepetitive and random obstacle avoidance tasks. First, a model-free DRL agent to plan velocity-bounded and obstacle-free motion is employed for a manipulator with 'n' degrees of freedom (DoF) in task space through joint-level reasoning. This plan is then input into a robust subsystem-based adaptive controller, which produces the necessary torques, while the Cuckoo Search Optimization (CSO) algorithm enhances control gains to minimize the time required to reach, time taken to stabilize, the maximum deviation from the desired value, and persistent tracking error in the steady state. This approach guarantees that position and velocity errors exponentially converge to zero, accounting for any initial and end-point variations, unknown modeling errors, and external disturbances. Theoretical assertions are validated through the presentation of simulation outcomes.
A better understanding of interactive pedestrian behavior in critical traffic situations is essential for the development of enhanced pedestrian safety systems. Real-world traffic observations play a decisive role in this, since they represent behavior in an unbiased way. In this work, we present an approach of how a subset of very considerable pedestrian-vehicle interactions can be derived from a camera-based observation system. For this purpose, we have examined road user trajectories automatically for establishing temporal and spatial relationships, using 110h hours of video recordings. In order to identify critical interactions, our approach combines the metric post-encroachment time with a newly introduced motion adaption metric. From more than 11,000 reconstructed pedestrian trajectories, 259 potential scenarios remained, using a post-encroachment time threshold of 2s. However, in 95% of cases, no adaptation of the pedestrian behavior was observed due to avoiding criticality. Applying the proposed motion adaption metric, only 21 critical scenarios remained. Manual investigations revealed that critical pedestrian vehicle interactions were present in 7 of those. They were further analyzed and made publicly available for developing pedestrian behavior models3. The results indicate that critical interactions in which the pedestrian perceives and reacts to the vehicle at a relatively late stage can be extracted using the proposed method.
Time-optimal control of a multi-rotor remains an open problem due to the under-actuation and nonlinearity of its dynamics, which make it difficult to solve this problem directly. In this paper, the time-optimal control problem of the multi-rotor is studied. Firstly, a thrust limit optimal decomposition method is proposed, which can reasonably decompose the limited thrust into three directions according to the current state and the target state. As a result, the thrust limit constraint is decomposed as a linear constraint. With the linear constraint and decoupled dynamics, a time-optimal guidance trajectory can be obtained. Then, a cost function is defined based on the time-optimal guidance trajectory, which has a quadratic form and can be used to evaluate the time-optimal performance of the system outputs. Finally, based on the cost function, the time-optimal control problem is reformulated as an MPC (Model Predictive Control) problem. The experimental results demonstrate the feasibility and validity of the proposed methods.
In large IT systems, software deployment is a crucial process in online services as their code is regularly updated. However, a faulty code change may degrade the target service's performance and cause cascading outages in downstream services. Thus, software deployments should be comprehensively monitored, and their anomalies should be detected timely. In this paper, we study the problem of anomaly detection for deployments. We begin by identifying the challenges unique to this anomaly detection problem, which is at entity-level (e.g., deployments), relative to the more typical problem of anomaly detection in multivariate time series (MTS). The unique challenges include the heterogeneity of deployments, the low latency tolerance, the ambiguous anomaly definition, and the limited supervision. To address them, we propose a novel framework, semi-supervised hybrid Model for Entity-Level Online Detection of anomalY (MELODY). MELODY first transforms the MTS of different entities to the same feature space by an online feature extractor, then uses a newly proposed semi-supervised deep one-class model for detecting anomalous entities. We evaluated MELODY on real data of cloud services with 1.2M+ time series. The relative F1 score improvement of MELODY over the state-of-the-art methods ranges from 7.6% to 56.5%. The user evaluation suggests MELODY is suitable for monitoring deployments in large online systems.
The distributional simplicity bias (DSB) posits that neural networks learn low-order moments of the data distribution first, before moving on to higher-order correlations. In this work, we present compelling new evidence for the DSB by showing that networks automatically learn to perform well on maximum-entropy distributions whose low-order statistics match those of the training set early in training, then lose this ability later. We also extend the DSB to discrete domains by proving an equivalence between token $n$-gram frequencies and the moments of embedding vectors, and by finding empirical evidence for the bias in LLMs. Finally we use optimal transport methods to surgically edit the low-order statistics of one class to match those of another, and show that early-training networks treat the edited samples as if they were drawn from the target class. Code is available at https://github.com/EleutherAI/features-across-time.
Robotic assistants reduce the manual efforts being put in by humans in their day-to-day tasks. In this paper, we develop a voice-controlled personal assistant robot. The robot takes the human voice commands by its own built-in microphone. This robot not only takes the commands and executes them but also acknowledges them through speech output. This robot can perform different movements, turns, wakeup/shutdown operations, relocate an object from one place to another, and can also develop a conversation with humans. The voice commands are processed in real time using an offline server. The speech signal commands are directly communicated to the server using a USB cable. The personal assistant robot is developed on a microcontroller-based platform. Performance evaluation is carried out with encouraging results of the initial experiments. Possible improvements for applications in homes, hospitals, car systems, and industries are also discussed.