Abstract

Accurately recognizing a revisited place is crucial for embodied agents to localize and navigate. This requires visual representations to be distinct, despite strong variations in camera viewpoint and scene appearance. Existing visual place recognition pipelines encode the whole image and search for matches. This poses a fundamental challenge in matching two images of the same place captured from different camera viewpoints: the similarity of what overlaps can be dominated by the dissimilarity of what does not overlap. We address this by encoding and searching for image segments instead of the whole images. We propose to use open-set image segmentation to decompose an image into `meaningful' entities (i.e., things and stuff). This enables us to create a novel image representation as a collection of multiple overlapping subgraphs connecting a segment with its neighboring segments, dubbed SuperSegment. Furthermore, to efficiently encode these SuperSegments into compact vector representations, we propose a novel factorized representation of feature aggregation. We show that retrieving these partial representations leads to significantly higher recognition recall than the typical whole image based retrieval. Our segments-based approach, dubbed SegVLAD, sets a new state-of-the-art in place recognition on a diverse selection of benchmark datasets, while being applicable to both generic and task-specialized image encoders. Finally, we demonstrate the potential of our method to revisit anything by evaluating our method on an object instance retrieval task, which bridges the two disparate areas of research: visual place recognition and object-goal navigation, through their common aim of recognizing goal objects specific to a place.

Abstract

Detecting objects under adverse weather and lighting conditions is crucial for the safe and continuous operation of an autonomous vehicle, and remains an unsolved problem. We present a Gated Differentiable Image Processing (GDIP) block, a domain-agnostic network architecture, which can be plugged into existing object detection networks (e.g., Yolo) and trained end-to-end with adverse condition images such as those captured under fog and low lighting. Our proposed GDIP block learns to enhance images directly through the downstream object detection loss. This is achieved by learning parameters of multiple image pre-processing (IP) techniques that operate concurrently, with their outputs combined using weights learned through a novel gating mechanism. We further improve GDIP through a multi-stage guidance procedure for progressive image enhancement. Finally, trading off accuracy for speed, we propose a variant of GDIP that can be used as a regularizer for training Yolo, which eliminates the need for GDIP-based image enhancement during inference, resulting in higher throughput and plausible real-world deployment. We demonstrate significant improvement in detection performance over several state-of-the-art methods through quantitative and qualitative studies on synthetic datasets such as PascalVOC, and real-world foggy (RTTS) and low-lighting (ExDark) datasets.

Abstract

We investigate the Vision-and-Language Navigation (VLN) problem in the context of autonomous driving in outdoor settings. We solve the problem by explicitly grounding the navigable regions corresponding to the textual command. At each timestamp, the model predicts a segmentation mask corresponding to the intermediate or the final navigable region. Our work contrasts with existing efforts in VLN, which pose this task as a node selection problem, given a discrete connected graph corresponding to the environment. We do not assume the availability of such a discretised map. Our work moves towards continuity in action space, provides interpretability through visual feedback and allows VLN on commands requiring finer manoeuvres like "park between the two cars". Furthermore, we propose a novel meta-dataset CARLA-NAV to allow efficient training and validation. The dataset comprises pre-recorded training sequences and a live environment for validation and testing. We provide extensive qualitative and quantitive empirical results to validate the efficacy of the proposed approach.

Abstract

The world we live in is full of technology and with each passing day the advancement and usage of UAVs increases efficiently. As a result of the many application scenarios, there are some missions where the UAVs are vulnerable to external disruptions, such as a ground station's loss of connectivity, security missions, safety concerns, and delivery-related missions. Therefore, depending on the scenario, this could affect the operations and result in the safe landing of UAVs. Hence, this paper presents a heuristic approach towards safe landing of multi-rotor UAVs in the dynamic environments. The aim of this approach is to detect safe potential landing zones - PLZ, and find out the best one to land in. The PLZ is initially, detected by processing an image through the canny edge algorithm, and then the diameter-area estimation is applied for each region with minimal edges. The spots that have a higher area than the vehicle's clearance are labeled as safe PLZ. Onto the second phase of this approach, the velocities of dynamic obstacles that are moving towards the PLZs are calculated and their time to reach the zones are taken into consideration. The ETA of the UAV is calculated and during the descending of UAV, the dynamic obstacle avoidance is executed. The approach tested on the real-world environments have shown better results from existing work.

Abstract

Autonomous driving requires accurate reasoning of the location of objects from raw sensor data. Recent end-to-end learning methods go from raw sensor data to a trajectory output via Bird’s Eye View(BEV) segmentation as an interpretable intermediate representation. Motion planning over cost maps generated via Birds Eye View (BEV) segmentation has emerged as a prominent approach in autonomous driving. However, the current approaches have two critical gaps. First, the optimization process is simplistic and involves just evaluating a fixed set of trajectories over the cost map. The trajectory samples are not adapted based on their associated cost values. Second, the existing cost maps do not account for the uncertainty in the cost maps that can arise due to noise in RGB images, BEV annotations etc. As a result, these approaches can struggle in challenging scenarios where there is abrupt cutin, stopping, overtaking, merging, etc from the neighbouring vehicles. In this paper, we propose UAP-BEV, a novel approach that models the noise in Spatio-Temporal BEV predictions to create an uncertainty-aware occupancy grid map. Using queries of the distance to the closest occupied cell, we obtain a sample estimate of the collision probability of the ego-vehicle. Subsequently, our approach uses gradient-free sampling-based optimization to compute low-cost trajectories over the cost

Abstract

Throwing motion is known for phenomenally fast rearrangement, sorting tasks, and placing the object outside the limited workspace with less effort. However, in the robotics domain, despite many simple yet versatile, mechanically intelligent grippers reported earlier, they fo- cus primarily on achieving robust grasping and dexterous manipulation. This article presents a novel design of a sin- gle actuator driven hybrid gripper with mechanically cou- pled rigid links and elastic gripping surface; this arrange- ment provides the dual function of versatile grasping and throwing manipulation. The gripper comprises a latching mechanism (LM) that drives two passive rigid fingers by elongating/releasing the coupled elastic strip. Elongating the gripping surface enables the gripper to adapt to ob- jects with different geometries, vary surface contact force characteristics, and store the energy in the form of elastic potential. A mechanism to discharge the stored potential energy gradually or instantaneously is essential when the intended task is to place the object free from impact or away from the limited reachable workspace. The proposed LM can swiftly shift from a quick release to a gradual release of the stored elastic potential for greater object’s accelera- tion during throwing and no acceleration while placing. By doing so, the object can be placed at the desired location even farther than the manipulator’s reachable workspace. We report the proposed gripper’s design details, develop- ment, and experimentally demonstrate the versatile grasp- ing, impact-free placing, and throwing capabilities. Index Terms—Gripper design, multipurpose gripper, non- prehensile manipulation, throwing.

Abstract

Humans have a natural ability to perform semantic associations with the surrounding objects in the environment. This allows them to create a mental map of the environment which helps them to navigate on-demand when given a linguistic instruction. A natural goal in Vision Language Navigation (VLN) research is to impart autonomous agents with similar capabilities. Recently introduced VL Maps \cite{huang23vlmaps} take a step towards this goal by creating a semantic spatial map representation of the environment without any labelled data. However, their representations are limited for practical applicability as they do not distinguish between different instances of the same object. In this work, we address this limitation by integrating instance-level information into spatial map representation using a community detection algorithm and by utilizing word ontology learned by large language models (LLMs) to perform open-set semantic associations in the mapping representation. The resulting map representation improves the navigation performance by two-fold (233\%) on realistic language commands with instance-specific descriptions compared to VL Maps. We validate the practicality and effectiveness of our approach through extensive qualitative and quantitative experiments.

Abstract

Autonomous driving requires accurate reasoning of the location of objects from raw sensor data. Recent end-to-end learning methods go from raw sensor data to a trajectory output via Bird’s Eye View(BEV) segmentation as an interpretable intermediate representation. Motion planning over cost maps generated via Birds Eye View (BEV) segmen- tation has emerged as a prominent approach in autonomous driving. However, the current approaches have two critical gaps. First, the optimization process is simplistic and involves just evaluating a fixed set of trajectories over the cost map. The trajectory samples are not adapted based on their associated cost values. Second, the existing cost maps do not account for the uncertainty in the cost maps that can arise due to noise in RGB images, BEV annotations. As a result, these approaches can struggle in challenging scenarios where there is abrupt cut-in, stopping, overtaking, merging, etc from the neighboring vehicles. In this paper, we propose UAP-BEV, a novel approach that models the noise in Spatio-Temporal BEV predictions to create an uncertainty-aware occupancy grid map. Using queries of the distance to the closest occupied cell, we obtain a sample estimate of the collision probability of the ego-vehicle. Subsequently, our approach uses gradient-free sampling-based optimization to compute low-cost trajectories over the cost map

Abstract

Coordinate-based implicit neural networks, or neural fields, have emerged as useful representations of shape and appearance in 3D computer vision. Despite advances, however, it remains challenging to build neural fields for categories of objects without datasets like ShapeNet that provide “canonicalized” object instances that are consistently aligned for their 3D position and orientation (pose).We present Canonical Field Network (CaFi-Net), a self-supervised method to canonicalize the 3D pose of instances from an object category represented as neural fields, specifically neural radiance fields (NeRFs). CaFi-Net directly learns from continuous and noisy radiance fields using a Siamese network architecture that is designed to extract equivariant field features for category-level canonicalization. During inference, our method takes pre-trained neural radiance fields of novel object instances at arbitrary 3D pose and estimates a canonical field with consistent 3D pose across the entire category. Extensive experiments on a new dataset of 1300 NeRF models across 13 object categories show that our method matches or exceeds the performance of 3D point cloud-based methods.

Abstract

This paper presents a real-time algorithm for computing the optimal sequence and motion plans for a fixed-base manipulator to pick and place a set of given objects. The optimality is defined in terms of the total execution time of the sequence or its proxy, the arc-length in the joint-space. The fundamental complexity stems from the fact that the optimality metric depends on the joint motion, but the task specification is in the end-effector space. Moreover, mapping between a pair of end-effector positions to the shortest arc-length joint trajectory is not analytic; instead, it entails solving a complex trajectory optimization problem. Existing works ignore this complex mapping and use the Euclidean distance in the end-effector space to compute the sequence. In this paper, we overcome the reliance on the Euclidean distance heuristic by introducing a novel data-driven technique to estimate the optimal arc-length cost in joint …