We study how group symmetry helps improve data efficiency and generalization for end-to-end differentiable planning algorithms when symmetry appears in decision-making tasks. Motivated by equivariant convolution networks, we treat the path planning problem as \textit{signals} over grids. We show that value iteration in this case is a linear equivariant operator, which is a (steerable) convolution. This extends Value Iteration Networks (VINs) on using convolutional networks for path planning with additional rotation and reflection symmetry. Our implementation is based on VINs and uses steerable convolution networks to incorporate symmetry. The experiments are performed on four tasks: 2D navigation, visual navigation, and 2 degrees of freedom (2DOFs) configuration space and workspace manipulation. Our symmetric planning algorithms improve training efficiency and generalization by large margins compared to non-equivariant counterparts, VIN and GPPN.
In audio-visual navigation (AVN), an intelligent agent needs to navigate to a constantly sound-making object in complex 3D environments based on its audio and visual perceptions. While existing methods attempt to improve the navigation performance with preciously designed path planning or intricate task settings, none has improved the model generalisation on unheard sounds with task settings unchanged. We thus propose a contrastive learning-based method to tackle this challenge by regularising the audio encoder, where the sound-agnostic goal-driven latent representations can be learnt from various audio signals of different classes. In addition, we consider two data augmentation strategies to enrich the training sounds. We demonstrate that our designs can be easily equipped to existing AVN frameworks to obtain an immediate performance gain (13.4%$\uparrow$ in SPL on Replica and 12.2%$\uparrow$ in SPL on MP3D). Our project is available at https://AV-GeN.github.io/.
Many scenes in real life can be abstracted to the sparse reward visual scenes, where it is difficult for an agent to tackle the task under the condition of only accepting images and sparse rewards. We propose to decompose this problem into two sub-problems: the visual representation and the sparse reward. To address them, a novel framework IAMMIR combining the self-supervised representation learning with the intrinsic motivation is presented. For visual representation, a representation driven by a combination of the imageaugmented forward dynamics and the reward is acquired. For sparse rewards, a new type of intrinsic reward is designed, the Momentum Memory Intrinsic Reward (MMIR). It utilizes the difference of the outputs from the current model (online network) and the historical model (target network) to present the agent's state familiarity. Our method is evaluated on the visual navigation task with sparse rewards in Vizdoom. Experiments demonstrate that our method achieves the state of the art performance in sample efficiency, at least 2 times faster than the existing methods reaching 100% success rate.
Understanding the geometric relationships between objects in a scene is a core capability in enabling both humans and autonomous agents to navigate in new environments. A sparse, unified representation of the scene topology will allow agents to act efficiently to move through their environment, communicate the environment state with others, and utilize the representation for diverse downstream tasks. To this end, we propose a method to train an autonomous agent to learn to accumulate a 3D scene graph representation of its environment by simultaneously learning to navigate through said environment. We demonstrate that our approach, GraphMapper, enables the learning of effective navigation policies through fewer interactions with the environment than vision-based systems alone. Further, we show that GraphMapper can act as a modular scene encoder to operate alongside existing Learning-based solutions to not only increase navigational efficiency but also generate intermediate scene representations that are useful for other future tasks.
This paper tackles the problem of learning value functions from undirected state-only experience (state transitions without action labels i.e. (s,s',r) tuples). We first theoretically characterize the applicability of Q-learning in this setting. We show that tabular Q-learning in discrete Markov decision processes (MDPs) learns the same value function under any arbitrary refinement of the action space. This theoretical result motivates the design of Latent Action Q-learning or LAQ, an offline RL method that can learn effective value functions from state-only experience. Latent Action Q-learning (LAQ) learns value functions using Q-learning on discrete latent actions obtained through a latent-variable future prediction model. We show that LAQ can recover value functions that have high correlation with value functions learned using ground truth actions. Value functions learned using LAQ lead to sample efficient acquisition of goal-directed behavior, can be used with domain-specific low-level controllers, and facilitate transfer across embodiments. Our experiments in 5 environments ranging from 2D grid world to 3D visual navigation in realistic environments demonstrate the benefits of LAQ over simpler alternatives, imitation learning oracles, and competing methods.
Visual object tracking is an important task in computer vision, which has many real-world applications, e.g., video surveillance, visual navigation. Visual object tracking also has many challenges, e.g., object occlusion and deformation. To solve above problems and track the target accurately and efficiently, many tracking algorithms have emerged in recent years. This paper presents the rationale and representative works of two most popular tracking frameworks in past ten years, i.e., the corelation filter and Siamese network for object tracking. Then we present some deep learning based tracking methods categorized by different network structures. We also introduce some classical strategies for handling the challenges in tracking problem. Further, this paper detailedly present and compare the benchmarks and challenges for tracking, from which we summarize the development history and development trend of visual tracking. Focusing on the future development of object tracking, which we think would be applied in real-world scenes before some problems to be addressed, such as the problems in long-term tracking, low-power high-speed tracking and attack-robust tracking. In the future, the integration of multimodal data, e.g., the depth image, thermal image with traditional color image, will provide more solutions for visual tracking. Moreover, tracking task will go together with some other tasks, e.g., video object detection and segmentation.
A key functional block of visual navigation system for intelligent autonomous vehicles is Loop Closure detection and subsequent relocalisation. State-of-the-Art methods still approach the problem as uni-directional along the direction of the previous motion. As a result, most of the methods fail in the absence of a significantly similar overlap of perspectives. In this study, we propose an approach for bi-directional loop closure. This will, for the first time, provide us with the capability to relocalize to a location even when traveling in the opposite direction, thus significantly reducing long-term odometry drift in the absence of a direct loop. We present a technique to select training data from large datasets in order to make them usable for the bi-directional problem. The data is used to train and validate two different CNN architectures for loop closure detection and subsequent regression of 6-DOF camera pose between the views in an end-to-end manner. The outcome packs a considerable impact and aids significantly to real-world scenarios that do not offer direct loop closure opportunities. We provide a rigorous empirical comparison against other established approaches and evaluate our method on both outdoor and indoor data from the FinnForest dataset and PennCOSYVIO dataset.
This paper studies category-level object pose estimation based on a single monocular image. Recent advances in pose-aware generative models have paved the way for addressing this challenging task using analysis-by-synthesis. The idea is to sequentially update a set of latent variables, e.g., pose, shape, and appearance, of the generative model until the generated image best agrees with the observation. However, convergence and efficiency are two challenges of this inference procedure. In this paper, we take a deeper look at the inference of analysis-by-synthesis from the perspective of visual navigation, and investigate what is a good navigation policy for this specific task. We evaluate three different strategies, including gradient descent, reinforcement learning and imitation learning, via thorough comparisons in terms of convergence, robustness and efficiency. Moreover, we show that a simple hybrid approach leads to an effective and efficient solution. We further compare these strategies to state-of-the-art methods, and demonstrate superior performance on synthetic and real-world datasets leveraging off-the-shelf pose-aware generative models.
This work introduces a simulator-based benchmark for visual localization in the autonomous navigation context. The dynamic benchmark enables investigation of how variables such as the time of day, weather, and camera perspective affect the navigation performance of autonomous agents that utilize visual localization for closed-loop control. The experimental part of the paper studies the effects of four such variables by evaluating state-of-the-art visual localization methods as part of the motion planning module of an autonomous navigation stack. The results show major variation in the suitability of the different methods for vision-based navigation. To the authors' best knowledge, the proposed benchmark is the first to study modern visual localization methods as part of a complete navigation stack. We make the benchmark available at https://github.com/lasuomela/carla_vloc_benchmark.
Pre-training has been adopted in a few of recent works for Vision-and-Language Navigation (VLN). However, previous pre-training methods for VLN either lack the ability to predict future actions or ignore the trajectory contexts, which are essential for a greedy navigation process. In this work, to promote the learning of spatio-temporal visual-textual correspondence as well as the agent's capability of decision making, we propose a novel history-and-order aware pre-training paradigm (HOP) with VLN-specific objectives that exploit the past observations and support future action prediction. Specifically, in addition to the commonly used Masked Language Modeling (MLM) and Trajectory-Instruction Matching (TIM), we design two proxy tasks to model temporal order information: Trajectory Order Modeling (TOM) and Group Order Modeling (GOM). Moreover, our navigation action prediction is also enhanced by introducing the task of Action Prediction with History (APH), which takes into account the history visual perceptions. Extensive experimental results on four downstream VLN tasks (R2R, REVERIE, NDH, RxR) demonstrate the effectiveness of our proposed method compared against several state-of-the-art agents.
The Perspective-n-Point problem aims to estimate the relative pose between a calibrated monocular camera and a known 3D model, by aligning pairs of 2D captured image points to their corresponding 3D points in the model. We suggest an algorithm that runs on weak IoT devices in real-time but still provides provable theoretical guarantees for both running time and correctness. Existing solvers provide only one of these requirements. Our main motivation was to turn the popular DJI's Tello Drone (<90gr, <\$100) into an autonomous drone that navigates in an indoor environment with no external human/laptop/sensor, by simply attaching a Raspberry PI Zero (<9gr, <\$25) to it. This tiny micro-processor takes as input a real-time video from a tiny RGB camera, and runs our PnP solver on-board. Extensive experimental results, open source code, and a demonstration video are included.
Following language instructions to navigate in unseen environments is a challenging problem for autonomous embodied agents. The agent not only needs to ground languages in visual scenes, but also should explore the environment to reach its target. In this work, we propose a dual-scale graph transformer (DUET) for joint long-term action planning and fine-grained cross-modal understanding. We build a topological map on-the-fly to enable efficient exploration in global action space. To balance the complexity of large action space reasoning and fine-grained language grounding, we dynamically combine a fine-scale encoding over local observations and a coarse-scale encoding on a global map via graph transformers. The proposed approach, DUET, significantly outperforms state-of-the-art methods on goal-oriented vision-and-language navigation (VLN) benchmarks REVERIE and SOON. It also improves the success rate on the fine-grained VLN benchmark R2R.
Audio-visual navigation task requires an agent to find a sound source in a realistic, unmapped 3D environment by utilizing egocentric audio-visual observations. Existing audio-visual navigation works assume a clean environment that solely contains the target sound, which, however, would not be suitable in most real-world applications due to the unexpected sound noise or intentional interference. In this work, we design an acoustically complex environment in which, besides the target sound, there exists a sound attacker playing a zero-sum game with the agent. More specifically, the attacker can move and change the volume and category of the sound to make the agent suffer from finding the sounding object while the agent tries to dodge the attack and navigate to the goal under the intervention. Under certain constraints to the attacker, we can improve the robustness of the agent towards unexpected sound attacks in audio-visual navigation. For better convergence, we develop a joint training mechanism by employing the property of a centralized critic with decentralized actors. Experiments on two real-world 3D scan datasets, Replica, and Matterport3D, verify the effectiveness and the robustness of the agent trained under our designed environment when transferred to the clean environment or the one containing sound attackers with random policy. Project: \url{https://yyf17.github.io/SAAVN}.
In reinforcement learning for visual navigation, it is common to develop a model for each new task, and train that model from scratch with task-specific interactions in 3D environments. However, this process is expensive; massive amounts of interactions are needed for the model to generalize well. Moreover, this process is repeated whenever there is a change in the task type or the goal modality. We present a unified approach to visual navigation using a novel modular transfer learning model. Our model can effectively leverage its experience from one source task and apply it to multiple target tasks (e.g., ObjectNav, RoomNav, ViewNav) with various goal modalities (e.g., image, sketch, audio, label). Furthermore, our model enables zero-shot experience learning, whereby it can solve the target tasks without receiving any task-specific interactive training. Our experiments on multiple photorealistic datasets and challenging tasks show that our approach learns faster, generalizes better, and outperforms SoTA models by a significant margin.
Recent work on audio-visual navigation targets a single static sound in noise-free audio environments and struggles to generalize to unheard sounds. We introduce the novel dynamic audio-visual navigation benchmark in which an embodied AI agent must catch a moving sound source in an unmapped environment in the presence of distractors and noisy sounds. We propose an end-to-end reinforcement learning approach that relies on a multi-modal architecture that fuses the spatial audio-visual information from a binaural audio signal and spatial occupancy maps to encode the features needed to learn a robust navigation policy for our new complex task settings. We demonstrate that our approach outperforms the current state-of-the-art with better generalization to unheard sounds and better robustness to noisy scenarios on the two challenging 3D scanned real-world datasets Replica and Matterport3D, for the static and dynamic audio-visual navigation benchmarks. Our novel benchmark will be made available at http://dav-nav.cs.uni-freiburg.de.
The gap between simulation and the real-world restrains many machine learning breakthroughs in computer vision and reinforcement learning from being applicable in the real world. In this work, we tackle this gap for the specific case of camera-based navigation, formulating it as following a visual cue in the foreground with arbitrary backgrounds. The visual cue in the foreground can often be simulated realistically, such as a line, gate or cone. The challenge then lies in coping with the unknown backgrounds and integrating both. As such, the goal is to train a visual agent on data captured in an empty simulated environment except for this foreground cue and test this model directly in a visually diverse real world. In order to bridge this big gap, we show it's crucial to combine following techniques namely: Randomized augmentation of the fore- and background, regularization with both deep supervision and triplet loss and finally abstraction of the dynamics by using waypoints rather than direct velocity commands. The various techniques are ablated in our experimental results both qualitatively and quantitatively finally demonstrating a successful transfer from simulation to the real world.
Deep reinforcement learning has shown promising results on an abundance of robotic tasks in simulation, including visual navigation and manipulation. Prior work generally aims to build embodied agents that solve their assigned tasks as quickly as possible, while largely ignoring the problems caused by collision with objects during interaction. This lack of prioritization is understandable: there is no inherent cost in breaking virtual objects. As a result, "well-trained" agents frequently collide with objects before achieving their primary goals, a behavior that would be catastrophic in the real world. In this paper, we study the problem of training agents to complete the task of visual mobile manipulation in the ManipulaTHOR environment while avoiding unnecessary collision (disturbance) with objects. We formulate disturbance avoidance as a penalty term in the reward function, but find that directly training with such penalized rewards often results in agents being unable to escape poor local optima. Instead, we propose a two-stage training curriculum where an agent is first allowed to freely explore and build basic competencies without penalization, after which a disturbance penalty is introduced to refine the agent's behavior. Results on testing scenes show that our curriculum not only avoids these poor local optima, but also leads to 10% absolute gains in success rate without disturbance, compared to our state-of-the-art baselines. Moreover, our curriculum is significantly more performant than a safe RL algorithm that casts collision avoidance as a constraint. Finally, we propose a novel disturbance-prediction auxiliary task that accelerates learning.
Visual exploration is a task that seeks to visit all the navigable areas of an environment as quickly as possible. The existing methods employ deep reinforcement learning (RL) as the standard tool for the task. However, they tend to be vulnerable to statistical shifts between the training and test data, resulting in poor generalization over novel environments that are out-of-distribution (OOD) from the training data. In this paper, we attempt to improve the generalization ability by utilizing the inductive biases available for the task. Employing the active neural SLAM (ANS) that learns exploration policies with the advantage actor-critic (A2C) method as the base framework, we first point out that the mappings represented by the actor and the critic should satisfy specific symmetries. We then propose a network design for the actor and the critic to inherently attain these symmetries. Specifically, we use $G$-convolution instead of the standard convolution and insert the semi-global polar pooling (SGPP) layer, which we newly design in this study, in the last section of the critic network. Experimental results show that our method increases area coverage by $8.1 m^2$ when trained on the Gibson dataset and tested on the MP3D dataset, establishing the new state-of-the-art.
We present a reward-predictive, model-based deep learning method featuring trajectory-constrained visual attention for local planning in visual navigation tasks. Our method learns to place visual attention at locations in latent image space which follow trajectories caused by vehicle control actions to enhance predictive accuracy during planning. The attention model is jointly optimized by the task-specific loss and an additional trajectory-constraint loss, allowing adaptability yet encouraging a regularized structure for improved generalization and reliability. Importantly, visual attention is applied in latent feature map space instead of raw image space to promote efficient planning. We validated our model in visual navigation tasks of planning low turbulence, collision-free trajectories in off-road settings and hill climbing with locking differentials in the presence of slippery terrain. Experiments involved randomized procedural generated simulation and real-world environments. We found our method improved generalization and learning efficiency when compared to no-attention and self-attention alternatives.
Instance object detection plays an important role in intelligent monitoring, visual navigation, human-computer interaction, intelligent services and other fields. Inspired by the great success of Deep Convolutional Neural Network (DCNN), DCNN-based instance object detection has become a promising research topic. To address the problem that DCNN always requires a large-scale annotated dataset to supervise its training while manual annotation is exhausting and time-consuming, we propose a new framework based on co-training called Gram Self-Labeling and Detection (Gram-SLD). The proposed Gram-SLD can automatically annotate a large amount of data with very limited manually labeled key data and achieve competitive performance. In our framework, gram loss is defined and used to construct two fully redundant and independent views and a key sample selection strategy along with an automatic annotating strategy that comprehensively consider precision and recall are proposed to generate high quality pseudo-labels. Experiments on the public GMU Kitchen Dataset , Active Vision Dataset and the self-made BHID-ITEM Datasetdemonstrate that, with only 5% labeled training data, our Gram-SLD achieves competitive performance in object detection (less than 2% mAP loss), compared with the fully supervised methods. In practical applications with complex and changing environments, the proposed method can satisfy the real-time and accuracy requirements on instance object detection.