Imagine-2-Drive: High-Fidelity World Modeling in CARLA for Autonomous Vehicles

In autonomous driving with image based state space, accurate prediction of future events and modeling diverse behavioral modes are essential for safety and effective decision-making. World model-based Reinforcement Learning (WMRL) approaches offers a promising solution by simulating future states from current state and actions. However, utility of world models is often limited by typical RL policies being limited to deterministic or single gaussian distribution. By failing to capture the full spectrum of possible actions, reduces their adaptability in complex, dynamic environments. In this work, we introduce Imagine-2-Drive, a framework that consists of two components, VISTAPlan, a high-fidelity world model for accurate future prediction and Diffusion Policy Actor (DPA), a diffusion based policy to model multi-modal behaviors for trajectory prediction. We use VISTAPlan to simulate and evaluate trajectories from DPA and use Denoising Diffusion Policy Optimization (DDPO) to train DPA to maximize the cumulative sum of rewards over the trajectories. We analyze the benefits of each component and the framework as a whole in CARLA with standard driving metrics. As a consequence of our twin novelties- VISTAPlan and DPA, we significantly outperform the state of the art (SOTA) world models on standard driving metrics by 15% and 20% on Route Completion and Success Rate respectively.

DA-VIL: Adaptive Dual-Arm Manipulation with Reinforcement Learning and Variable Impedance Control

Dual-arm manipulation is an area of growing interest in the robotics community. Enabling robots to perform tasks that require the coordinated use of two arms, is essential for complex manipulation tasks such as handling large objects, assembling components, and performing human-like interactions. However, achieving effective dual-arm manipulation is challenging due to the need for precise coordination, dynamic adaptability, and the ability to manage interaction forces between the arms and the objects being manipulated. We propose a novel pipeline that combines the advantages of policy learning based on environment feedback and gradient-based optimization to learn controller gains required for the control outputs. This allows the robotic system to dynamically modulate its impedance in response to task demands, ensuring stability and dexterity in dual-arm operations. We evaluate our pipeline on a trajectory-tracking task involving a variety of large, complex objects with different masses and geometries. The performance is then compared to three other established methods for controlling dual-arm robots, demonstrating superior results.

Towards Global Localization using Multi-Modal Object-Instance Re-Identification

Re-identification (ReID) is a critical challenge in computer vision, predominantly studied in the context of pedestrians and vehicles. However, robust object-instance ReID, which has significant implications for tasks such as autonomous exploration, long-term perception, and scene understanding, remains underexplored. In this work, we address this gap by proposing a novel dual-path object-instance re-identification transformer architecture that integrates multimodal RGB and depth information. By leveraging depth data, we demonstrate improvements in ReID across scenes that are cluttered or have varying illumination conditions. Additionally, we develop a ReID-based localization framework that enables accurate camera localization and pose identification across different viewpoints. We validate our methods using two custom-built RGB-D datasets, as well as multiple sequences from the open-source TUM RGB-D datasets. Our approach demonstrates significant improvements in both object instance ReID (mAP of 75.18) and localization accuracy (success rate of 83% on TUM-RGBD), highlighting the essential role of object ReID in advancing robotic perception. Our models, frameworks, and datasets have been made publicly available.

Constrained 6-DoF Grasp Generation on Complex Shapes for Improved Dual-Arm Manipulation

Efficiently generating grasp poses tailored to specific regions of an object is vital for various robotic manipulation tasks, especially in a dual-arm setup. This scenario presents a significant challenge due to the complex geometries involved, requiring a deep understanding of the local geometry to generate grasps efficiently on the specified constrained regions. Existing methods only explore settings involving table-top/small objects and require augmented datasets to train, limiting their performance on complex objects. We propose CGDF: Constrained Grasp Diffusion Fields, a diffusion-based grasp generative model that generalizes to objects with arbitrary geometries, as well as generates dense grasps on the target regions. CGDF uses a part-guided diffusion approach that enables it to get high sample efficiency in constrained grasping without explicitly training on massive constraint-augmented datasets. We provide qualitative and quantitative comparisons using analytical metrics and in simulation, in both unconstrained and constrained settings to show that our method can generalize to generate stable grasps on complex objects, especially useful for dual-arm manipulation settings, while existing methods struggle to do so.

DiffPrompter: Differentiable Implicit Visual Prompts for Semantic-Segmentation in Adverse Conditions

Semantic segmentation in adverse weather scenarios is a critical task for autonomous driving systems. While foundation models have shown promise, the need for specialized adaptors becomes evident for handling more challenging scenarios. We introduce DiffPrompter, a novel differentiable visual and latent prompting mechanism aimed at expanding the learning capabilities of existing adaptors in foundation models. Our proposed $\nabla$HFC image processing block excels particularly in adverse weather conditions, where conventional methods often fall short. Furthermore, we investigate the advantages of jointly training visual and latent prompts, demonstrating that this combined approach significantly enhances performance in out-of-distribution scenarios. Our differentiable visual prompts leverage parallel and series architectures to generate prompts, effectively improving object segmentation tasks in adverse conditions. Through a comprehensive series of experiments and evaluations, we provide empirical evidence to support the efficacy of our approach. Project page at https://diffprompter.github.io.

HyP-NeRF: Learning Improved NeRF Priors using a HyperNetwork

Neural Radiance Fields (NeRF) have become an increasingly popular representation to capture high-quality appearance and shape of scenes and objects. However, learning generalizable NeRF priors over categories of scenes or objects has been challenging due to the high dimensionality of network weight space. To address the limitations of existing work on generalization, multi-view consistency and to improve quality, we propose HyP-NeRF, a latent conditioning method for learning generalizable category-level NeRF priors using hypernetworks. Rather than using hypernetworks to estimate only the weights of a NeRF, we estimate both the weights and the multi-resolution hash encodings resulting in significant quality gains. To improve quality even further, we incorporate a denoise and finetune strategy that denoises images rendered from NeRFs estimated by the hypernetwork and finetunes it while retaining multiview consistency. These improvements enable us to use HyP-NeRF as a generalizable prior for multiple downstream tasks including NeRF reconstruction from single-view or cluttered scenes and text-to-NeRF. We provide qualitative comparisons and evaluate HyP-NeRF on three tasks: generalization, compression, and retrieval, demonstrating our state-of-the-art results.

GDIP: Gated Differentiable Image Processing for Object-Detection in Adverse Conditions

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.

Approaches and Challenges in Robotic Perception for Table-top Rearrangement and Planning

Table-top Rearrangement and Planning is a challenging problem that relies heavily on an excellent perception stack. The perception stack involves observing and registering the 3D scene on the table, detecting what objects are on the table, and how to manipulate them. Consequently, it greatly influences the system's task-planning and motion-planning stacks that follow. We present a comprehensive overview and discuss the different challenges associated with the perception module. This work is a result of our extensive involvement in the ICRA 2022 Open Cloud Robot Table Organization Challenge, in which we currently stand first on the leaderboard (as of 24th of April 2022, the final week of the challenge).

UrbanFly: Uncertainty-Aware Planning for Navigation Amongst High-Rises with Monocular Visual-Inertial SLAM Maps

We present UrbanFly: an uncertainty-aware real-time planning framework for quadrotor navigation in urban high-rise environments. A core aspect of UrbanFly is its ability to robustly plan directly on the sparse point clouds generated by a Monocular Visual Inertial SLAM (VINS) backend. It achieves this by using the sparse point clouds to build an uncertainty-integrated cuboid representation of the environment through a data-driven monocular plane segmentation network. Our chosen world model provides faster distance queries than the more common voxel-grid representation, and UrbanFly leverages this capability in two different ways leading to as many trajectory optimizers. The first optimizer uses a gradient-free cross-entropy method to compute trajectories that minimize collision probability and smoothness cost. Our second optimizer is a simplified version of the first and uses a sequential convex programming optimizer initialized based on probabilistic safety estimates on a set of randomly drawn trajectories. Both our trajectory optimizers are made computationally tractable and independent of the nature of underlying uncertainty by embedding the distribution of collision violations in Reproducing Kernel Hilbert Space. Empowered by the algorithmic innovation, UrbanFly outperforms competing baselines in metrics such as collision rate, trajectory length, etc., on a high fidelity AirSim simulator augmented with synthetic and real-world dataset scenes.

Grounding Linguistic Commands to Navigable Regions

Humans have a natural ability to effortlessly comprehend linguistic commands such as "park next to the yellow sedan" and instinctively know which region of the road the vehicle should navigate. Extending this ability to autonomous vehicles is the next step towards creating fully autonomous agents that respond and act according to human commands. To this end, we propose the novel task of Referring Navigable Regions (RNR), i.e., grounding regions of interest for navigation based on the linguistic command. RNR is different from Referring Image Segmentation (RIS), which focuses on grounding an object referred to by the natural language expression instead of grounding a navigable region. For example, for a command "park next to the yellow sedan," RIS will aim to segment the referred sedan, and RNR aims to segment the suggested parking region on the road. We introduce a new dataset, Talk2Car-RegSeg, which extends the existing Talk2car dataset with segmentation masks for the regions described by the linguistic commands. A separate test split with concise manoeuvre-oriented commands is provided to assess the practicality of our dataset. We benchmark the proposed dataset using a novel transformer-based architecture. We present extensive ablations and show superior performance over baselines on multiple evaluation metrics. A downstream path planner generating trajectories based on RNR outputs confirms the efficacy of the proposed framework.