David Hsu

Mikko Lauri, David Hsu, Joni Pajarinen

Noisy sensing, imperfect control, and environment changes are defining characteristics of many real-world robot tasks. The partially observable Markov decision process (POMDP) provides a principled mathematical framework for modeling and solving robot decision and control tasks under uncertainty. Over the last decade, it has seen many successful applications, spanning localization and navigation, search and tracking, autonomous driving, multi-robot systems, manipulation, and human-robot interaction. This survey aims to bridge the gap between the development of POMDP models and algorithms at one end and application to diverse robot decision tasks at the other. It analyzes the characteristics of these tasks and connects them with the mathematical and algorithmic properties of the POMDP framework for effective modeling and solution. For practitioners, the survey provides some of the key task characteristics in deciding when and how to apply POMDPs to robot tasks successfully. For POMDP algorithm designers, the survey provides new insights into the unique challenges of applying POMDPs to robot systems and points to promising new directions for further research.

Yiqing Xu, Wei Gao, David Hsu

Inverse reinforcement learning (IRL) seeks to infer a cost function that explains the underlying goals and preferences of expert demonstrations. This paper presents receding horizon inverse reinforcement learning (RHIRL), a new IRL algorithm for high-dimensional, noisy, continuous systems with black-box dynamic models. RHIRL addresses two key challenges of IRL: scalability and robustness. To handle high-dimensional continuous systems, RHIRL matches the induced optimal trajectories with expert demonstrations locally in a receding horizon manner and 'stitches' together the local solutions to learn the cost; it thereby avoids the 'curse of dimensionality'. This contrasts sharply with earlier algorithms that match with expert demonstrations globally over the entire high-dimensional state space. To be robust against imperfect expert demonstrations and control noise, RHIRL learns a state-dependent cost function 'disentangled' from system dynamics under mild conditions. Experiments on benchmark tasks show that RHIRL outperforms several leading IRL algorithms in most instances. We also prove that the cumulative error of RHIRL grows linearly with the task duration.

Zirui Zhao, Wee Sun Lee, David Hsu

We present a new method, PARsing And visual GrOuNding (ParaGon), for grounding natural language in object placement tasks. Natural language generally describes objects and spatial relations with compositionality and ambiguity, two major obstacles to effective language grounding. For compositionality, ParaGon parses a language instruction into an object-centric graph representation to ground objects individually. For ambiguity, ParaGon uses a novel particle-based graph neural network to reason about object placements with uncertainty. Essentially, ParaGon integrates a parsing algorithm into a probabilistic, data-driven learning framework. It is fully differentiable and trained end-to-end from data for robustness against complex, ambiguous language input.

Mohamad H. Danesh, Panpan Cai, David Hsu

Uncertainty on human behaviors poses a significant challenge to autonomous driving in crowded urban environments. The partially observable Markov decision processes (POMDPs) offer a principled framework for planning under uncertainty, often leveraging Monte Carlo sampling to achieve online performance for complex tasks. However, sampling also raises safety concerns by potentially missing critical events. To address this, we propose a new algorithm, LEarning Attention over Driving bEhavioRs (LEADER), that learns to attend to critical human behaviors during planning. LEADER learns a neural network generator to provide attention over human behaviors in real-time situations. It integrates the attention into a belief-space planner, using importance sampling to bias reasoning towards critical events. To train the algorithm, we let the attention generator and the planner form a min-max game. By solving the min-max game, LEADER learns to perform risk-aware planning without human labeling.

Yiyuan Lee, Katie Lee, Panpan Cai et al.

Identifying internal parameters for planning is crucial to maximizing the performance of a planner. However, automatically tuning internal parameters which are conditioned on the problem instance is especially challenging. A recent line of work focuses on learning planning parameter generators, but lack a consistent problem definition and software framework. This work proposes the unified planner optimization problem (POP) formulation, along with the Open Planner Optimization Framework (OPOF), a highly extensible software framework to specify and to solve these problems in a reusable manner.

Soujanya Poria, Navonil Majumder, Chia-Yu Hung et al.

Due to their ability of follow natural language instructions, vision-language-action (VLA) models are increasingly prevalent in the embodied AI arena, following the widespread success of their precursors -- LLMs and VLMs. In this paper, we discuss 10 principal milestones in the ongoing development of VLA models -- multimodality, reasoning, data, evaluation, cross-robot action generalization, efficiency, whole-body coordination, safety, agents, and coordination with humans. Furthermore, we discuss the emerging trends of using spatial understanding, modeling world dynamics, post training, and data synthesis -- all aiming to reach these milestones. Through these discussions, we hope to bring attention to the research avenues that may accelerate the development of VLA models into wider acceptability.

Yiqing Xu, David Hsu

Tidying up a messy table may appear simple for humans, but articulating clear criteria for tidiness is challenging due to the ambiguous nature of common sense reasoning. Large Language Models (LLMs) have proven capable of capturing common sense knowledge to reason over this vague concept of tidiness. However, they alone may struggle with table tidying due to the limited grasp on the spatio-visual aspects of tidiness. In this work, we aim to ground the common-sense concept of tidiness within the context of object arrangement. Our survey reveals that humans usually factorize tidiness into semantic and visual-spatial tidiness; our grounding approach aligns with this decomposition. We connect a language-based policy generator with an image-based tidiness score function: the policy generator utilizes the LLM's commonsense knowledge to cluster objects by their implicit types and functionalities for semantic tidiness; meanwhile, the tidiness score function assesses the visual-spatial relations of the object to achieve visual-spatial tidiness. Our tidiness score is trained using synthetic data generated cheaply from customized random walks, which inherently encode the order of tidiness, thereby bypassing the need for labor-intensive human demonstrations. The simulated experiment shows that our approach successfully generates tidy arrangements, predominately in 2D, with potential for 3D stacking, for tables with various novel objects.

Yiqing Xu, Finale Doshi-Velez, David Hsu

Inverse reinforcement learning (IRL) algorithms often rely on (forward) reinforcement learning or planning, over a given time horizon, to compute an approximately optimal policy for a hypothesized reward function; they then match this policy with expert demonstrations. The time horizon plays a critical role in determining both the accuracy of reward estimates and the computational efficiency of IRL algorithms. Interestingly, an *effective time horizon* shorter than the ground-truth value often produces better results faster. This work formally analyzes this phenomenon and provides an explanation: the time horizon controls the complexity of an induced policy class and mitigates overfitting with limited data. This analysis provides a guide for the principled choice of the effective horizon for IRL. It also prompts us to re-examine the classic IRL formulation: it is more natural to learn jointly the reward and the effective horizon rather than the reward alone with a given horizon. To validate our findings, we implement a cross-validation extension and the experimental results support the theoretical analysis. The project page and code are publicly available.

Phong Tran, Haoran Wu, Cunjun Yu et al.

Trajectory prediction plays a vital role in the performance of autonomous driving systems, and prediction accuracy, such as average displacement error (ADE) or final displacement error (FDE), is widely used as a performance metric. However, a significant disparity exists between the accuracy of predictors on fixed datasets and driving performance when the predictors are used downstream for vehicle control, because of a dynamics gap. In the real world, the prediction algorithm influences the behavior of the ego vehicle, which, in turn, influences the behaviors of other vehicles nearby. This interaction results in predictor-specific dynamics that directly impacts prediction results. In fixed datasets, since other vehicles' responses are predetermined, this interaction effect is lost, leading to a significant dynamics gap. This paper studies the overlooked significance of this dynamics gap. We also examine several other factors contributing to the disparity between prediction performance and driving performance. The findings highlight the trade-off between the predictor's computational efficiency and prediction accuracy in determining real-world driving performance. In summary, an interactive, task-driven evaluation protocol for trajectory prediction is crucial to capture its effectiveness for autonomous driving. Source code along with experimental settings is available online.

Nuwan Janaka, Shengdong Zhao, David Hsu et al.

Advanced digital assistants can significantly enhance task performance, reduce user burden, and provide personalized guidance to improve users' abilities. However, the development of such intelligent digital assistants presents a formidable challenge. To address this, we introduce TOM, a conceptual architecture and software platform (https://github.com/TOM-Platform) designed to support the development of intelligent wearable assistants that are contextually aware of both the user and the environment. This system was developed collaboratively with AR/MR researchers, HCI researchers, AI/Robotic researchers, and software developers, and it continues to evolve to meet the diverse requirements of these stakeholders. TOM facilitates the creation of intelligent assistive AR applications for daily activities and supports the recording and analysis of user interactions, integration of new devices, and the provision of assistance for various activities. Additionally, we showcase several proof-of-concept assistive services and discuss the challenges involved in developing such services.

Anxing Xiao, Nuwan Janaka, Tianrun Hu et al.

Imagine a future when we can Zoom-call a robot to manage household chores remotely. This work takes one step in this direction. Robi Butler is a new household robot assistant that enables seamless multimodal remote interaction. It allows the human user to monitor its environment from a first-person view, issue voice or text commands, and specify target objects through hand-pointing gestures. At its core, a high-level behavior module, powered by Large Language Models (LLMs), interprets multimodal instructions to generate multistep action plans. Each plan consists of open-vocabulary primitives supported by vision-language models, enabling the robot to process both textual and gestural inputs. Zoom provides a convenient interface to implement remote interactions between the human and the robot. The integration of these components allows Robi Butler to ground remote multimodal instructions in real-world home environments in a zero-shot manner. We evaluated the system on various household tasks, demonstrating its ability to execute complex user commands with multimodal inputs. We also conducted a user study to examine how multimodal interaction influences user experiences in remote human-robot interaction. These results suggest that with the advances in robot foundation models, we are moving closer to the reality of remote household robot assistants.

Bo Ai, Zhanxin Wu, David Hsu

The data-driven approach to robot control has been gathering pace rapidly, yet generalization to unseen task domains remains a critical challenge. We argue that the key to generalization is representations that are (i) rich enough to capture all task-relevant information and (ii) invariant to superfluous variability between the training and the test domains. We experimentally study such a representation -- containing both depth and semantic information -- for visual navigation and show that it enables a control policy trained entirely in simulated indoor scenes to generalize to diverse real-world environments, both indoors and outdoors. Further, we show that our representation reduces the A-distance between the training and test domains, improving the generalization error bound as a result. Our proposed approach is scalable: the learned policy improves continuously, as the foundation models that it exploits absorb more diverse data during pre-training.

Siwei Chen, Anxing Xiao, David Hsu

This work addresses the problem of long-horizon task planning with the Large Language Model (LLM) in an open-world household environment. Existing works fail to explicitly track key objects and attributes, leading to erroneous decisions in long-horizon tasks, or rely on highly engineered state features and feedback, which is not generalizable. We propose an open state representation that provides continuous expansion and updating of object attributes from the LLM's inherent capabilities for context understanding and historical action reasoning. Our proposed representation maintains a comprehensive record of an object's attributes and changes, enabling robust retrospective summary of the sequence of actions leading to the current state. This allows continuously updating world model to enhance context understanding for decision-making in task planning. We validate our model through experiments across simulated and real-world task planning scenarios, demonstrating significant improvements over baseline methods in a variety of tasks requiring long-horizon state tracking and reasoning. (Video\footnote{Video demonstration: \url{https://youtu.be/QkN-8pxV3Mo}.})

Yuhong Deng, David Hsu

Clothes manipulation is a critical capability for household robots; yet, existing methods are often confined to specific tasks, such as folding or flattening, due to the complex high-dimensional geometry of deformable fabric. This paper presents CLothes mAnipulation with Semantic keyPoints (CLASP) for general-purpose clothes manipulation, which enables the robot to perform diverse manipulation tasks over different types of clothes. The key idea of CLASP is semantic keypoints -- e.g., "right shoulder", "left sleeve", etc. -- a sparse spatial-semantic representation that is salient for both perception and action. Semantic keypoints of clothes can be effectively extracted from depth images and are sufficient to represent a broad range of clothes manipulation policies. CLASP leverages semantic keypoints to bridge LLM-powered task planning and low-level action execution in a two-level hierarchy. Extensive simulation experiments show that CLASP outperforms baseline methods across diverse clothes types in both seen and unseen tasks. Further, experiments with a Kinova dual-arm system on four distinct tasks -- folding, flattening, hanging, and placing -- confirm CLASP's performance on a real robot.

Chao Tang, Anxing Xiao, Yuhong Deng et al.

Imitating tool manipulation from human videos offers an intuitive approach to teaching robots, while also providing a promising and scalable alternative to labor-intensive teleoperation data collection for visuomotor policy learning. While humans can mimic tool manipulation behavior by observing others perform a task just once and effortlessly transfer the skill to diverse tools for functionally equivalent tasks, current robots struggle to achieve this level of generalization. A key challenge lies in establishing function-level correspondences, considering the significant geometric variations among functionally similar tools, referred to as intra-function variations. To address this challenge, we propose MimicFunc, a framework that establishes functional correspondences with function frame, a function-centric local coordinate frame constructed with keypoint-based abstraction, for imitating tool manipulation skills. Experiments demonstrate that MimicFunc effectively enables the robot to generalize the skill from a single RGB-D human video to manipulating novel tools for functionally equivalent tasks. Furthermore, leveraging MimicFunc's one-shot generalization capability, the generated rollouts can be used to train visuomotor policies without requiring labor-intensive teleoperation data collection for novel objects. Our code and video are available at https://sites.google.com/view/mimicfunc.

Xiao Ma, Siwei Chen, David Hsu et al.

Deep reinforcement learning (DRL) has achieved significant success in various robot tasks: manipulation, navigation, etc. However, complex visual observations in natural environments remains a major challenge. This paper presents Contrastive Variational Reinforcement Learning (CVRL), a model-based method that tackles complex visual observations in DRL. CVRL learns a contrastive variational model by maximizing the mutual information between latent states and observations discriminatively, through contrastive learning. It avoids modeling the complex observation space unnecessarily, as the commonly used generative observation model often does, and is significantly more robust. CVRL achieves comparable performance with state-of-the-art model-based DRL methods on standard Mujoco tasks. It significantly outperforms them on Natural Mujoco tasks and a robot box-pushing task with complex observations, e.g., dynamic shadows. The CVRL code is available publicly at https://github.com/Yusufma03/CVRL.

Panpan Cai, Yiyuan Lee, Yuanfu Luo et al.

Autonomous driving in an unregulated urban crowd is an outstanding challenge, especially, in the presence of many aggressive, high-speed traffic participants. This paper presents SUMMIT, a high-fidelity simulator that facilitates the development and testing of crowd-driving algorithms. By leveraging the open-source OpenStreetMap map database and a heterogeneous multi-agent motion prediction model developed in our earlier work, SUMMIT simulates dense, unregulated urban traffic for heterogeneous agents at any worldwide locations that OpenStreetMap supports. SUMMIT is built as an extension of CARLA and inherits from it the physics and visual realism for autonomous driving simulation. SUMMIT supports a wide range of applications, including perception, vehicle control and planning, and end-to-end learning. We provide a context-aware planner together with benchmark scenarios and show that SUMMIT generates complex, realistic traffic behaviors in challenging crowd-driving settings.

Yuanfu Luo, Panpan Cai, Yiyuan Lee et al.

This paper presents GAMMA, a general motion prediction model that enables large-scale real-time simulation and planning for autonomous driving. GAMMA models heterogeneous, interactive traffic agents. They operate under diverse road conditions, with various geometric and kinematic constraints. GAMMA treats the prediction task as constrained optimization in traffic agents' velocity space. The objective is to optimize an agent's driving performance, while obeying all the constraints resulting from the agent's kinematics, collision avoidance with other agents, and the environmental context. Further, GAMMA explicitly conditions the prediction on human behavioral states as parameters of the optimization model, in order to account for versatile human behaviors. We evaluated GAMMA on a set of real-world benchmark datasets. The results show that GAMMA achieves high prediction accuracy on both homogeneous and heterogeneous traffic datasets, with sub-millisecond execution time. Further, the computational efficiency and the flexibility of GAMMA enable (i) simulation of mixed urban traffic at many locations worldwide and (ii) planning for autonomous driving in dense traffic with uncertain driver behaviors, both in real-time. The open-source code of GAMMA is available online.

Chao Tang, Anxing Xiao, Yuhong Deng et al.

Learning tool use from a single human demonstration video offers a highly intuitive and efficient approach to robot teaching. While humans can effortlessly generalize a demonstrated tool manipulation skill to diverse tools that support the same function (e.g., pouring with a mug versus a teapot), current one-shot imitation learning (OSIL) methods struggle to achieve this. A key challenge lies in establishing functional correspondences between demonstration and test tools, considering significant geometric variations among tools with the same function (i.e., intra-function variations). To address this challenge, we propose FUNCTO (Function-Centric OSIL for Tool Manipulation), an OSIL method that establishes function-centric correspondences with a 3D functional keypoint representation, enabling robots to generalize tool manipulation skills from a single human demonstration video to novel tools with the same function despite significant intra-function variations. With this formulation, we factorize FUNCTO into three stages: (1) functional keypoint extraction, (2) function-centric correspondence establishment, and (3) functional keypoint-based action planning. We evaluate FUNCTO against exiting modular OSIL methods and end-to-end behavioral cloning methods through real-robot experiments on diverse tool manipulation tasks. The results demonstrate the superiority of FUNCTO when generalizing to novel tools with intra-function geometric variations. More details are available at https://sites.google.com/view/functo.

Wei Gao, David Hsu, Wee Sun Lee

An inverse reinforcement learning (IRL) agent learns to act intelligently by observing expert demonstrations and learning the expert's underlying reward function. Although learning the reward functions from demonstrations has achieved great success in various tasks, several other challenges are mostly ignored. Firstly, existing IRL methods try to learn the reward function from scratch without relying on any prior knowledge. Secondly, traditional IRL methods assume the reward functions are homogeneous across all the demonstrations. Some existing IRL methods managed to extend to the heterogeneous demonstrations. However, they still assume one hidden variable that affects the behavior and learn the underlying hidden variable together with the reward from demonstrations. To solve these issues, we present Context Hierarchy IRL(CHIRL), a new IRL algorithm that exploits the context to scale up IRL and learn reward functions of complex behaviors. CHIRL models the context hierarchically as a directed acyclic graph; it represents the reward function as a corresponding modular deep neural network that associates each network module with a node of the context hierarchy. The context hierarchy and the modular reward representation enable data sharing across multiple contexts and state abstraction, significantly improving the learning performance. CHIRL has a natural connection with hierarchical task planning when the context hierarchy represents subtask decomposition. It enables to incorporate the prior knowledge of causal dependencies of subtasks and make it capable of solving large complex tasks by decoupling it into several subtasks and conquering each subtask to solve the original task. Experiments on benchmark tasks, including a large scale autonomous driving task in the CARLA simulator, show promising results in scaling up IRL for tasks with complex reward functions.

Bo Ai, Wei Gao, Vinay et al.

How can a robot navigate successfully in rich and diverse environments, indoors or outdoors, along office corridors or trails on the grassland, on the flat ground or the staircase? To this end, this work aims to address three challenges: (i) complex visual observations, (ii) partial observability of local visual sensing, and (iii) multimodal robot behaviors conditioned on both the local environment and the global navigation objective. We propose to train a neural network (NN) controller for local navigation via imitation learning. To tackle complex visual observations, we extract multi-scale spatial representations through CNNs. To tackle partial observability, we aggregate multi-scale spatial information over time and encode it in LSTMs. To learn multimodal behaviors, we use a separate memory module for each behavior mode. Importantly, we integrate the multiple neural network modules into a unified controller that achieves robust performance for visual navigation in complex, partially observable environments. We implemented the controller on the quadrupedal Spot robot and evaluated it on three challenging tasks: adversarial pedestrian avoidance, blind-spot obstacle avoidance, and elevator riding. The experiments show that the proposed NN architecture significantly improves navigation performance.

Hanbo Zhang, Yunfan Lu, Cunjun Yu et al.

This paper presents INVIGORATE, a robot system that interacts with human through natural language and grasps a specified object in clutter. The objects may occlude, obstruct, or even stack on top of one another. INVIGORATE embodies several challenges: (i) infer the target object among other occluding objects, from input language expressions and RGB images, (ii) infer object blocking relationships (OBRs) from the images, and (iii) synthesize a multi-step plan to ask questions that disambiguate the target object and to grasp it successfully. We train separate neural networks for object detection, for visual grounding, for question generation, and for OBR detection and grasping. They allow for unrestricted object categories and language expressions, subject to the training datasets. However, errors in visual perception and ambiguity in human languages are inevitable and negatively impact the robot's performance. To overcome these uncertainties, we build a partially observable Markov decision process (POMDP) that integrates the learned neural network modules. Through approximate POMDP planning, the robot tracks the history of observations and asks disambiguation questions in order to achieve a near-optimal sequence of actions that identify and grasp the target object. INVIGORATE combines the benefits of model-based POMDP planning and data-driven deep learning. Preliminary experiments with INVIGORATE on a Fetch robot show significant benefits of this integrated approach to object grasping in clutter with natural language interactions. A demonstration video is available at https://youtu.be/zYakh80SGcU.

Siwei Chen, Xiao Ma, Yunfan Lu et al.

This paper presents Particle-based Object Manipulation (Prompt), a new approach to robot manipulation of novel objects ab initio, without prior object models or pre-training on a large object data set. The key element of Prompt is a particle-based object representation, in which each particle represents a point in the object, the local geometric, physical, and other features of the point, and also its relation with other particles. Like the model-based analytic approaches to manipulation, the particle representation enables the robot to reason about the object's geometry and dynamics in order to choose suitable manipulation actions. Like the data-driven approaches, the particle representation is learned online in real-time from visual sensor input, specifically, multi-view RGB images. The particle representation thus connects visual perception with robot control. Prompt combines the benefits of both model-based reasoning and data-driven learning. We show empirically that Prompt successfully handles a variety of everyday objects, some of which are transparent. It handles various manipulation tasks, including grasping, pushing, etc,. Our experiments also show that Prompt outperforms a state-of-the-art data-driven grasping method on the daily objects, even though it does not use any offline training data.

Peter Karkus, Shaojun Cai, David Hsu

Simultaneous localization and mapping (SLAM) remains challenging for a number of downstream applications, such as visual robot navigation, because of rapid turns, featureless walls, and poor camera quality. We introduce the Differentiable SLAM Network (SLAM-net) along with a navigation architecture to enable planar robot navigation in previously unseen indoor environments. SLAM-net encodes a particle filter based SLAM algorithm in a differentiable computation graph, and learns task-oriented neural network components by backpropagating through the SLAM algorithm. Because it can optimize all model components jointly for the end-objective, SLAM-net learns to be robust in challenging conditions. We run experiments in the Habitat platform with different real-world RGB and RGB-D datasets. SLAM-net significantly outperforms the widely adapted ORB-SLAM in noisy conditions. Our navigation architecture with SLAM-net improves the state-of-the-art for the Habitat Challenge 2020 PointNav task by a large margin (37% to 64% success). Project website: http://sites.google.com/view/slamnet

Xiao Ma, David Hsu, Wee Sun Lee

Manipulating deformable objects, such as ropes and clothing, is a long-standing challenge in robotics, because of their large degrees of freedom, complex non-linear dynamics, and self-occlusion in visual perception. The key difficulty is a suitable representation, rich enough to capture the object shape, dynamics for manipulation and yet simple enough to be estimated reliably from visual observations. This work aims to learn latent Graph dynamics for DefOrmable Object Manipulation (G-DOOM). G-DOOM approximates a deformable object as a sparse set of interacting keypoints, which are extracted automatically from images via unsupervised learning. It learns a graph neural network that captures abstractly the geometry and the interaction dynamics of the keypoints. To handle object self-occlusion, G-DOOM uses a recurrent neural network to track the keypoints over time and condition their interactions on the history. We then train the resulting recurrent graph dynamics model through contrastive learning in a high-fidelity simulator. For manipulation planning, G-DOOM reasons explicitly about the learned dynamics model through model-predictive control applied at each keypoint. Preliminary experiments of G-DOOM on a set of challenging rope and cloth manipulation tasks indicate strong performance, compared with state-of-the-art methods. Although trained in a simulator, G-DOOM transfers directly to a real robot for both rope and cloth manipulation.

Panpan Cai, David Hsu

Real-time planning under uncertainty is critical for robots operating in complex dynamic environments. Consider, for example, an autonomous robot vehicle driving in dense, unregulated urban traffic of cars, motorcycles, buses, etc. The robot vehicle has to plan in both short and long terms, in order to interact with many traffic participants with uncertain intentions and drive effectively. Planning explicitly over a long time horizon, however, incurs prohibitive computational costs and is impractical under real-time constraints. To achieve real-time performance for large-scale planning, this work introduces a new algorithm Learning from Tree Search for Driving (LeTS-Drive), which integrates planning and learning in a closed loop, and applies it to autonomous driving in crowded urban traffic in simulation. Specifically, LeTS-Drive learns a policy and its value function from data provided by an online planner, which searches a sparsely-sampled belief tree; the online planner in turn uses the learned policy and value functions as heuristics to scale up its run-time performance for real-time robot control. These two steps are repeated to form a closed loop so that the planner and the learner inform each other and improve in synchrony. The algorithm learns on its own in a self-supervised manner, without human effort on explicit data labeling. Experimental results demonstrate that LeTS-Drive outperforms either planning or learning alone, as well as open-loop integration of planning and learning.

Yuanfu Luo, Panpan Cai, Yiyuan Lee et al.

Autonomous driving in an unregulated urban crowd is an outstanding challenge, especially, in the presence of many aggressive, high-speed traffic participants. This paper presents SUMMIT, a high-fidelity simulator that facilitates the development and testing of crowd-driving algorithms. SUMMIT simulates dense, unregulated urban traffic at any worldwide locations as supported by the OpenStreetMap. The core of SUMMIT is a multi-agent motion model, GAMMA, that models the behaviours of heterogeneous traffic agents, and a real-time POMDP planner, Context-POMDP, that serves as a driving expert. SUMMIT is built as an extension of CARLA and inherits from it the physical and visual realism for autonomous driving simulation. SUMMIT supports a wide range of applications, including perception, vehicle control or planning, and end-to-end learning. We validate the realism of our motion model using its traffic motion prediction accuracy on various real-world data sets. We also provide several real-world benchmark scenarios to show that SUMMIT simulates complex, realistic traffic behaviors, and Context-POMDP drives safely and efficiently in challenging crowd-driving settings.

Yiyuan Lee, Panpan Cai, David Hsu

The partially observable Markov decision process (POMDP) is a principled general framework for robot decision making under uncertainty, but POMDP planning suffers from high computational complexity, when long-term planning is required. While temporally-extended macro-actions help to cut down the effective planning horizon and significantly improve computational efficiency, how do we acquire good macro-actions? This paper proposes Macro-Action Generator-Critic (MAGIC), which performs offline learning of macro-actions optimized for online POMDP planning. Specifically, MAGIC learns a macro-action generator end-to-end, using an online planner's performance as the feedback. During online planning, the generator generates on the fly situation-aware macro-actions conditioned on the robot's belief and the environment context. We evaluated MAGIC on several long-horizon planning tasks both in simulation and on a real robot. The experimental results show that the learned macro-actions offer significant benefits in online planning performance, compared with primitive actions and handcrafted macro-actions.

Siwei Chen, Xiao Ma, David Hsu

It has been arduous to assess the progress of a policy learning algorithm in the domain of hierarchical task with high dimensional action space due to the lack of a commonly accepted benchmark. In this work, we propose a new light-weight benchmark task called Diner Dash for evaluating the performance in a complicated task with high dimensional action space. In contrast to the traditional Atari games that only have a flat structure of goals and very few actions, the proposed benchmark task has a hierarchical task structure and size of 57 for the action space and hence can facilitate the development of policy learning in complicated tasks. On top of that, we introduce Decomposed Policy Graph Modelling (DPGM), an algorithm that combines both graph modelling and deep learning to allow explicit domain knowledge embedding and achieves significant improvement comparing to the baseline. In the experiments, we have shown the effectiveness of the domain knowledge injection via a specially designed imitation algorithm as well as results of other popular algorithms.

Xiao Ma, Peter Karkus, David Hsu et al.

Deep reinforcement learning is successful in decision making for sophisticated games, such as Atari, Go, etc. However, real-world decision making often requires reasoning with partial information extracted from complex visual observations. This paper presents Discriminative Particle Filter Reinforcement Learning (DPFRL), a new reinforcement learning framework for complex partial observations. DPFRL encodes a differentiable particle filter in the neural network policy for explicit reasoning with partial observations over time. The particle filter maintains a belief using learned discriminative update, which is trained end-to-end for decision making. We show that using the discriminative update instead of standard generative models results in significantly improved performance, especially for tasks with complex visual observations, because they circumvent the difficulty of modeling complex observations that are irrelevant to decision making. In addition, to extract features from the particle belief, we propose a new type of belief feature based on the moment generating function. DPFRL outperforms state-of-the-art POMDP RL models in Flickering Atari Games, an existing POMDP RL benchmark, and in Natural Flickering Atari Games, a new, more challenging POMDP RL benchmark introduced in this paper. Further, DPFRL performs well for visual navigation with real-world data in the Habitat environment.

Yaqi Xie, Indu P Bodala, Desmond C. Ong et al.

In this paper, we present results from a human-subject study designed to explore two facets of human mental models of robots---inferred capability and intention---and their relationship to overall trust and eventual decisions. In particular, we examine delegation situations characterized by uncertainty, and explore how inferred capability and intention are applied across different tasks. We develop an online survey where human participants decide whether to delegate control to a simulated UAV agent. Our study shows that human estimations of robot capability and intent correlate strongly with overall self-reported trust. However, overall trust is not independently sufficient to determine whether a human will decide to trust (delegate) a given task to a robot. Instead, our study reveals that estimations of robot intention, capability, and overall trust are integrated when deciding to delegate. From a broader perspective, these results suggest that calibrating overall trust alone is insufficient; to make correct decisions, humans need (and use) multi-faceted mental models when collaborating with robots across multiple contexts.

Hanbo Zhang, Site Bai, Xuguang Lan et al.

Reinforcement Learning(RL) with sparse rewards is a major challenge. We propose \emph{Hindsight Trust Region Policy Optimization}(HTRPO), a new RL algorithm that extends the highly successful TRPO algorithm with \emph{hindsight} to tackle the challenge of sparse rewards. Hindsight refers to the algorithm's ability to learn from information across goals, including ones not intended for the current task. HTRPO leverages two main ideas. It introduces QKL, a quadratic approximation to the KL divergence constraint on the trust region, leading to reduced variance in KL divergence estimation and improved stability in policy update. It also presents Hindsight Goal Filtering(HGF) to select conductive hindsight goals. In experiments, we evaluate HTRPO in various sparse reward tasks, including simple benchmarks, image-based Atari games, and simulated robot control. Ablation studies indicate that QKL and HGF contribute greatly to learning stability and high performance. Comparison results show that in all tasks, HTRPO consistently outperforms both TRPO and HPG, a state-of-the-art algorithm for RL with sparse rewards.

Xiao Ma, Peter Karkus, David Hsu et al.

Recurrent neural networks (RNNs) have been extraordinarily successful for prediction with sequential data. To tackle highly variable and noisy real-world data, we introduce Particle Filter Recurrent Neural Networks (PF-RNNs), a new RNN family that explicitly models uncertainty in its internal structure: while an RNN relies on a long, deterministic latent state vector, a PF-RNN maintains a latent state distribution, approximated as a set of particles. For effective learning, we provide a fully differentiable particle filter algorithm that updates the PF-RNN latent state distribution according to the Bayes rule. Experiments demonstrate that the proposed PF-RNNs outperform the corresponding standard gated RNNs on a synthetic robot localization dataset and 10 real-world sequence prediction datasets for text classification, stock price prediction, etc.

Panpan Cai, Yuanfu Luo, Aseem Saxena et al.

Autonomous driving in a crowded environment, e.g., a busy traffic intersection, is an unsolved challenge for robotics. The robot vehicle must contend with a dynamic and partially observable environment, noisy sensors, and many agents. A principled approach is to formalize it as a Partially Observable Markov Decision Process (POMDP) and solve it through online belief-tree search. To handle a large crowd and achieve real-time performance in this very challenging setting, we propose LeTS-Drive, which integrates online POMDP planning and deep learning. It consists of two phases. In the offline phase, we learn a policy and the corresponding value function by imitating the belief tree search. In the online phase, the learned policy and value function guide the belief tree search. LeTS-Drive leverages the robustness of planning and the runtime efficiency of learning to enhance the performance of both. Experimental results in simulation show that LeTS-Drive outperforms either planning or imitation learning alone and develops sophisticated driving skills.

Peter Karkus, Xiao Ma, David Hsu et al.

This paper introduces the Differentiable Algorithm Network (DAN), a composable architecture for robot learning systems. A DAN is composed of neural network modules, each encoding a differentiable robot algorithm and an associated model; and it is trained end-to-end from data. DAN combines the strengths of model-driven modular system design and data-driven end-to-end learning. The algorithms and models act as structural assumptions to reduce the data requirements for learning; end-to-end learning allows the modules to adapt to one another and compensate for imperfect models and algorithms, in order to achieve the best overall system performance. We illustrate the DAN methodology through a case study on a simulated robot system, which learns to navigate in complex 3-D environments with only local visual observations and an image of a partially correct 2-D floor map.

Robert Pinsler, Peter Karkus, Andras Kupcsik et al.

Scarce data is a major challenge to scaling robot learning to truly complex tasks, as we need to generalize locally learned policies over different task contexts. Contextual policy search offers data-efficient learning and generalization by explicitly conditioning the policy on a parametric context space. In this paper, we further structure the contextual policy representation. We propose to factor contexts into two components: target contexts that describe the task objectives, e.g. target position for throwing a ball; and environment contexts that characterize the environment, e.g. initial position or mass of the ball. Our key observation is that experience can be directly generalized over target contexts. We show that this can be easily exploited in contextual policy search algorithms. In particular, we apply factorization to a Bayesian optimization approach to contextual policy search both in sampling-based and active learning settings. Our simulation results show faster learning and better generalization in various robotic domains. See our supplementary video: https://youtu.be/MNTbBAOufDY.

Min Chen, David Hsu, Wee Sun Lee

Robot understanding of human intentions is essential for fluid human-robot interaction. Intentions, however, cannot be directly observed and must be inferred from behaviors. We learn a model of adaptive human behavior conditioned on the intention as a latent variable. We then embed the human behavior model into a principled probabilistic decision model, which enables the robot to (i) explore actively in order to infer human intentions and (ii) choose actions that maximize its performance. Furthermore, the robot learns from the demonstrated actions of human experts to further improve exploration. Preliminary experiments in simulation indicate that our approach, when applied to autonomous driving, improves the efficiency and safety of driving in common interactive driving scenarios.

Peter Karkus, David Hsu, Wee Sun Lee

We propose to take a novel approach to robot system design where each building block of a larger system is represented as a differentiable program, i.e. a deep neural network. This representation allows for integrating algorithmic planning and deep learning in a principled manner, and thus combine the benefits of model-free and model-based methods. We apply the proposed approach to a challenging partially observable robot navigation task. The robot must navigate to a goal in a previously unseen 3-D environment without knowing its initial location, and instead relying on a 2-D floor map and visual observations from an onboard camera. We introduce the Navigation Networks (NavNets) that encode state estimation, planning and acting in a single, end-to-end trainable recurrent neural network. In preliminary simulation experiments we successfully trained navigation networks to solve the challenging partially observable navigation task.

Harold Soh, Yaqi Xie, Min Chen et al.

Trust is essential in shaping human interactions with one another and with robots. This paper discusses how human trust in robot capabilities transfers across multiple tasks. We first present a human-subject study of two distinct task domains: a Fetch robot performing household tasks and a virtual reality simulation of an autonomous vehicle performing driving and parking maneuvers. The findings expand our understanding of trust and inspire new differentiable models of trust evolution and transfer via latent task representations: (i) a rational Bayes model, (ii) a data-driven neural network model, and (iii) a hybrid model that combines the two. Experiments show that the proposed models outperform prevailing models when predicting trust over unseen tasks and users. These results suggest that (i) task-dependent functional trust models capture human trust in robot capabilities more accurately, and (ii) trust transfer across tasks can be inferred to a good degree. The latter enables trust-mediated robot decision-making for fluent human-robot interaction in multi-task settings.

Mohit Shridhar, David Hsu

This paper presents INGRESS, a robot system that follows human natural language instructions to pick and place everyday objects. The core issue here is the grounding of referring expressions: infer objects and their relationships from input images and language expressions. INGRESS allows for unconstrained object categories and unconstrained language expressions. Further, it asks questions to disambiguate referring expressions interactively. To achieve these, we take the approach of grounding by generation and propose a two-stage neural network model for grounding. The first stage uses a neural network to generate visual descriptions of objects, compares them with the input language expression, and identifies a set of candidate objects. The second stage uses another neural network to examine all pairwise relations between the candidates and infers the most likely referred object. The same neural networks are used for both grounding and question generation for disambiguation. Experiments show that INGRESS outperformed a state-of-the-art method on the RefCOCO dataset and in robot experiments with humans.

Yuanfu Luo, Panpan Cai, Aniket Bera et al.

This paper presents a planning system for autonomous driving among many pedestrians. A key ingredient of our approach is PORCA, a pedestrian motion prediction model that accounts for both a pedestrian's global navigation intention and local interactions with the vehicle and other pedestrians. Unfortunately, the autonomous vehicle does not know the pedestrian's intention a priori and requires a planning algorithm that hedges against the uncertainty in pedestrian intentions. Our planning system combines a POMDP algorithm with the pedestrian motion model and runs in near real time. Experiments show that it enables a robot vehicle to drive safely, efficiently, and smoothly among a crowd with a density of nearly one person per square meter.

Peter Karkus, David Hsu, Wee Sun Lee

Particle filtering is a powerful approach to sequential state estimation and finds application in many domains, including robot localization, object tracking, etc. To apply particle filtering in practice, a critical challenge is to construct probabilistic system models, especially for systems with complex dynamics or rich sensory inputs such as camera images. This paper introduces the Particle Filter Network (PFnet), which encodes both a system model and a particle filter algorithm in a single neural network. The PF-net is fully differentiable and trained end-to-end from data. Instead of learning a generic system model, it learns a model optimized for the particle filter algorithm. We apply the PF-net to a visual localization task, in which a robot must localize in a rich 3-D world, using only a schematic 2-D floor map. In simulation experiments, PF-net consistently outperforms alternative learning architectures, as well as a traditional model-based method, under a variety of sensor inputs. Further, PF-net generalizes well to new, unseen environments.

Panpan Cai, Yuanfu Luo, David Hsu et al.

Planning under uncertainty is critical for robust robot performance in uncertain, dynamic environments, but it incurs high computational cost. State-of-the-art online search algorithms, such as DESPOT, have vastly improved the computational efficiency of planning under uncertainty and made it a valuable tool for robotics in practice. This work takes one step further by leveraging both CPU and GPU parallelization in order to achieve near real-time online planning performance for complex tasks with large state, action, and observation spaces. Specifically, we propose Hybrid Parallel DESPOT (HyP-DESPOT), a massively parallel online planning algorithm that integrates CPU and GPU parallelism in a multi-level scheme. It performs parallel DESPOT tree search by simultaneously traversing multiple independent paths using multi-core CPUs and performs parallel Monte-Carlo simulations at the leaf nodes of the search tree using GPUs. Experimental results show that HyP-DESPOT speeds up online planning by up to several hundred times, compared with the original DESPOT algorithm, in several challenging robotic tasks in simulation.

Min Chen, Stefanos Nikolaidis, Harold Soh et al.

Trust in autonomy is essential for effective human-robot collaboration and user adoption of autonomous systems such as robot assistants. This paper introduces a computational model which integrates trust into robot decision-making. Specifically, we learn from data a partially observable Markov decision process (POMDP) with human trust as a latent variable. The trust-POMDP model provides a principled approach for the robot to (i) infer the trust of a human teammate through interaction, (ii) reason about the effect of its own actions on human trust, and (iii) choose actions that maximize team performance over the long term. We validated the model through human subject experiments on a table-clearing task in simulation (201 participants) and with a real robot (20 participants). In our studies, the robot builds human trust by manipulating low-risk objects first. Interestingly, the robot sometimes fails intentionally in order to modulate human trust and achieve the best team performance. These results show that the trust-POMDP calibrates trust to improve human-robot team performance over the long term. Further, they highlight that maximizing trust alone does not always lead to the best performance.

Wei Gao, David Hsu, Wee Sun Lee et al.

How can a delivery robot navigate reliably to a destination in a new office building, with minimal prior information? To tackle this challenge, this paper introduces a two-level hierarchical approach, which integrates model-free deep learning and model-based path planning. At the low level, a neural-network motion controller, called the intention-net, is trained end-to-end to provide robust local navigation. The intention-net maps images from a single monocular camera and "intentions" directly to robot controls. At the high level, a path planner uses a crude map, e.g., a 2-D floor plan, to compute a path from the robot's current location to the goal. The planned path provides intentions to the intention-net. Preliminary experiments suggest that the learned motion controller is robust against perceptual uncertainty and by integrating with a path planner, it generalizes effectively to new environments and goals.

Mohit Shridhar, David Hsu

The human language is one of the most natural interfaces for humans to interact with robots. This paper presents a robot system that retrieves everyday objects with unconstrained natural language descriptions. A core issue for the system is semantic and spatial grounding, which is to infer objects and their spatial relationships from images and natural language expressions. We introduce a two-stage neural-network grounding pipeline that maps natural language referring expressions directly to objects in the images. The first stage uses visual descriptions in the referring expressions to generate a candidate set of relevant objects. The second stage examines all pairwise relationships between the candidates and predicts the most likely referred object according to the spatial descriptions in the referring expressions. A key feature of our system is that by leveraging a large dataset of images labeled with text descriptions, it allows unrestricted object types and natural language referring expressions. Preliminary results indicate that our system outperforms a near state-of-the-art object comprehension system on standard benchmark datasets. We also present a robot system that follows voice commands to pick and place previously unseen objects.

Stefanos Nikolaidis, Jodi Forlizzi, David Hsu et al.

A robot operating in isolation needs to reason over the uncertainty in its model of the world and adapt its own actions to account for this uncertainty. Similarly, a robot interacting with people needs to reason over its uncertainty over the human internal state, as well as over how this state may change, as humans adapt to the robot. This paper summarizes our own work in this area, which depicts the different ways that probabilistic planning and game-theoretic algorithms can enable such reasoning in robotic systems that collaborate with people. We start with a general formulation of the problem as a two-player game with incomplete information. We then articulate the different assumptions within this general formulation, and we explain how these lead to exciting and diverse robot behaviors in real-time interactions with actual human subjects, in a variety of manufacturing, personal robotics and assistive care settings.

Peter Karkus, David Hsu, Wee Sun Lee

This paper introduces the QMDP-net, a neural network architecture for planning under partial observability. The QMDP-net combines the strengths of model-free learning and model-based planning. It is a recurrent policy network, but it represents a policy for a parameterized set of tasks by connecting a model with a planning algorithm that solves the model, thus embedding the solution structure of planning in a network learning architecture. The QMDP-net is fully differentiable and allows for end-to-end training. We train a QMDP-net on different tasks so that it can generalize to new ones in the parameterized task set and "transfer" to other similar tasks beyond the set. In preliminary experiments, QMDP-net showed strong performance on several robotic tasks in simulation. Interestingly, while QMDP-net encodes the QMDP algorithm, it sometimes outperforms the QMDP algorithm in the experiments, as a result of end-to-end learning.

Peter Karkus, Andras Kupcsik, David Hsu et al.

Scarce data is a major challenge to scaling robot learning to truly complex tasks, as we need to generalize locally learned policies over different "contexts". Bayesian optimization approaches to contextual policy search (CPS) offer data-efficient policy learning that generalize over a context space. We propose to improve data-efficiency by factoring typically considered contexts into two components: target-type contexts that correspond to a desired outcome of the learned behavior, e.g. target position for throwing a ball; and environment type contexts that correspond to some state of the environment, e.g. initial ball position or wind speed. Our key observation is that experience can be directly generalized over target-type contexts. Based on that we introduce Factored Contextual Policy Search with Bayesian Optimization for both passive and active learning settings. Preliminary results show faster policy generalization on a simulated toy problem. A full paper extension is available at arXiv:1904.11761

Nan Ye, Adhiraj Somani, David Hsu et al.

The partially observable Markov decision process (POMDP) provides a principled general framework for planning under uncertainty, but solving POMDPs optimally is computationally intractable, due to the "curse of dimensionality" and the "curse of history". To overcome these challenges, we introduce the Determinized Sparse Partially Observable Tree (DESPOT), a sparse approximation of the standard belief tree, for online planning under uncertainty. A DESPOT focuses online planning on a set of randomly sampled scenarios and compactly captures the "execution" of all policies under these scenarios. We show that the best policy obtained from a DESPOT is near-optimal, with a regret bound that depends on the representation size of the optimal policy. Leveraging this result, we give an anytime online planning algorithm, which searches a DESPOT for a policy that optimizes a regularized objective function. Regularization balances the estimated value of a policy under the sampled scenarios and the policy size, thus avoiding overfitting. The algorithm demonstrates strong experimental results, compared with some of the best online POMDP algorithms available. It has also been incorporated into an autonomous driving system for real-time vehicle control. The source code for the algorithm is available online.