Swarm-Gen: Fast Generation of Diverse Feasible Swarm Behaviors

Coordination behavior in robot swarms is inherently multi-modal in nature. That is, there are numerous ways in which a swarm of robots can avoid inter-agent collisions and reach their respective goals. However, the problem of generating diverse and feasible swarm behaviors in a scalable manner remains largely unaddressed. In this paper, we fill this gap by combining generative models with a safety-filter (SF). Specifically, we sample diverse trajectories from a learned generative model which is subsequently projected onto the feasible set using the SF. We experiment with two choices for generative models, namely: Conditional Variational Autoencoder (CVAE) and Vector-Quantized Variational Autoencoder (VQ-VAE). We highlight the trade-offs these two models provide in terms of computation time and trajectory diversity. We develop a custom solver for our SF and equip it with a neural network that predicts context-specific initialization. Thecinitialization network is trained in a self-supervised manner, taking advantage of the differentiability of the SF solver. We provide two sets of empirical results. First, we demonstrate that we can generate a large set of multi-modal, feasible trajectories, simulating diverse swarm behaviors, within a few tens of milliseconds. Second, we show that our initialization network provides faster convergence of our SF solver vis-a-vis other alternative heuristics.

Trajectory Optimization Under Stochastic Dynamics Leveraging Maximum Mean Discrepancy

This paper addresses sampling-based trajectory optimization for risk-aware navigation under stochastic dynamics. Typically such approaches operate by computing $\tilde{N}$ perturbed rollouts around the nominal dynamics to estimate the collision risk associated with a sequence of control commands. We consider a setting where it is expensive to estimate risk using perturbed rollouts, for example, due to expensive collision-checks. We put forward two key contributions. First, we develop an algorithm that distills the statistical information from a larger set of rollouts to a reduced-set with sample size $N<<\tilde{N}$. Consequently, we estimate collision risk using just $N$ rollouts instead of $\tilde{N}$. Second, we formulate a novel surrogate for the collision risk that can leverage the distilled statistical information contained in the reduced-set. We formalize both algorithmic contributions using distribution embedding in Reproducing Kernel Hilbert Space (RKHS) and Maximum Mean Discrepancy (MMD). We perform extensive benchmarking to demonstrate that our MMD-based approach leads to safer trajectories at low sample regime than existing baselines using Conditional Value-at Risk (CVaR) based collision risk estimate.

MMD-OPT : Maximum Mean Discrepancy Based Sample Efficient Collision Risk Minimization for Autonomous Driving

We propose MMD-OPT: a sample-efficient approach for minimizing the risk of collision under arbitrary prediction distribution of the dynamic obstacles. MMD-OPT is based on embedding distribution in Reproducing Kernel Hilbert Space (RKHS) and the associated Maximum Mean Discrepancy (MMD). We show how these two concepts can be used to define a sample efficient surrogate for collision risk estimate. We perform extensive simulations to validate the effectiveness of MMD-OPT on both synthetic and real-world datasets. Importantly, we show that trajectory optimization with our MMD-based collision risk surrogate leads to safer trajectories at low sample regimes than popular alternatives based on Conditional Value at Risk (CVaR).

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.

CrowdSurfer: Sampling Optimization Augmented with Vector-Quantized Variational AutoEncoder for Dense Crowd Navigation

Navigation amongst densely packed crowds remains a challenge for mobile robots. The complexity increases further if the environment layout changes, making the prior computed global plan infeasible. In this paper, we show that it is possible to dramatically enhance crowd navigation by just improving the local planner. Our approach combines generative modelling with inference time optimization to generate sophisticated long-horizon local plans at interactive rates. More specifically, we train a Vector Quantized Variational AutoEncoder to learn a prior over the expert trajectory distribution conditioned on the perception input. At run-time, this is used as an initialization for a sampling-based optimizer for further refinement. Our approach does not require any sophisticated prediction of dynamic obstacles and yet provides state-of-the-art performance. In particular, we compare against the recent DRL-VO approach and show a 40% improvement in success rate and a 6% improvement in travel time.

Differentiable-Optimization Based Neural Policy for Occlusion-Aware Target Tracking

Tracking a target in cluttered and dynamic environments is challenging but forms a core component in applications like aerial cinematography. The obstacles in the environment not only pose collision risk but can also occlude the target from the field-of-view of the robot. Moreover, the target future trajectory may be unknown and only its current state can be estimated. In this paper, we propose a learned probabilistic neural policy for safe, occlusion-free target tracking. The core novelty of our work stems from the structure of our policy network that combines generative modeling based on Conditional Variational Autoencoder (CVAE) with differentiable optimization layers. The role of the CVAE is to provide a base trajectory distribution which is then projected onto a learned feasible set through the optimization layer. Furthermore, both the weights of the CVAE network and the parameters of the differentiable optimization can be learned in an end-to-end fashion through demonstration trajectories. We improve the state-of-the-art (SOTA) in the following respects. We show that our learned policy outperforms existing SOTA in terms of occlusion/collision avoidance capabilities and computation time. Second, we present an extensive ablation showing how different components of our learning pipeline contribute to the overall tracking task. We also demonstrate the real-time performance of our approach on resource-constrained hardware such as NVIDIA Jetson TX2. Finally, our learned policy can also be viewed as a reactive planner for navigation in highly cluttered environments.

Bi-level Trajectory Optimization on Uneven Terrains with Differentiable Wheel-Terrain Interaction Model

Navigation of wheeled vehicles on uneven terrain necessitates going beyond the 2D approaches for trajectory planning. Specifically, it is essential to incorporate the full 6dof variation of vehicle pose and its associated stability cost in the planning process. To this end, most recent works aim to learn a neural network model to predict the vehicle evolution. However, such approaches are data-intensive and fraught with generalization issues. In this paper, we present a purely model-based approach that just requires the digital elevation information of the terrain. Specifically, we express the wheel-terrain interaction and 6dof pose prediction as a non-linear least squares (NLS) problem. As a result, trajectory planning can be viewed as a bi-level optimization. The inner optimization layer predicts the pose on the terrain along a given trajectory, while the outer layer deforms the trajectory itself to reduce the stability and kinematic costs of the pose. We improve the state-of-the-art in the following respects. First, we show that our NLS based pose prediction closely matches the output from a high-fidelity physics engine. This result coupled with the fact that we can query gradients of the NLS solver, makes our pose predictor, a differentiable wheel-terrain interaction model. We further leverage this differentiability to efficiently solve the proposed bi-level trajectory optimization problem. Finally, we perform extensive experiments, and comparison with a baseline to showcase the effectiveness of our approach in obtaining smooth, stable trajectories.

LeGo-Drive: Language-enhanced Goal-oriented Closed-Loop End-to-End Autonomous Driving

Existing Vision-Language models (VLMs) estimate either long-term trajectory waypoints or a set of control actions as a reactive solution for closed-loop planning based on their rich scene comprehension. However, these estimations are coarse and are subjective to their "world understanding" which may generate sub-optimal decisions due to perception errors. In this paper, we introduce LeGo-Drive, which aims to address this issue by estimating a goal location based on the given language command as an intermediate representation in an end-to-end setting. The estimated goal might fall in a non-desirable region, like on top of a car for a parking-like command, leading to inadequate planning. Hence, we propose to train the architecture in an end-to-end manner, resulting in iterative refinement of both the goal and the trajectory collectively. We validate the effectiveness of our method through comprehensive experiments conducted in diverse simulated environments. We report significant improvements in standard autonomous driving metrics, with a goal reaching Success Rate of 81%. We further showcase the versatility of LeGo-Drive across different driving scenarios and linguistic inputs, underscoring its potential for practical deployment in autonomous vehicles and intelligent transportation systems.

Learning Sampling Distribution and Safety Filter for Autonomous Driving with VQ-VAE and Differentiable Optimization

Sampling trajectories from a distribution followed by ranking them based on a specified cost function is a common approach in autonomous driving. Typically, the sampling distribution is hand-crafted (e.g a Gaussian, or a grid). Recently, there have been efforts towards learning the sampling distribution through generative models such as Conditional Variational Autoencoder (CVAE). However, these approaches fail to capture the multi-modality of the driving behaviour due to the Gaussian latent prior of the CVAE. Thus, in this paper, we re-imagine the distribution learning through vector quantized variational autoencoder (VQ-VAE), whose discrete latent-space is well equipped to capture multi-modal sampling distribution. The VQ-VAE is trained with demonstration data of optimal trajectories. We further propose a differentiable optimization based safety filter to minimally correct the VQVAE sampled trajectories to ensure collision avoidance. We use backpropagation through the optimization layers in a self-supervised learning set-up to learn good initialization and optimal parameters of the safety filter. We perform extensive comparisons with state-of-the-art CVAE-based baseline in dense and aggressive traffic scenarios and show a reduction of up to 12 times in collision-rate while being competitive in driving speeds.

End-to-End Learning of Behavioural Inputs for Autonomous Driving in Dense Traffic

Trajectory sampling in the Frenet(road-aligned) frame, is one of the most popular methods for motion planning of autonomous vehicles. It operates by sampling a set of behavioural inputs, such as lane offset and forward speed, before solving a trajectory optimization problem conditioned on the sampled inputs. The sampling is handcrafted based on simple heuristics, does not adapt to driving scenarios, and is oblivious to the capabilities of downstream trajectory planners. In this paper, we propose an end-to-end learning of behavioural input distribution from expert demonstrations or in a self-supervised manner. Our core novelty lies in embedding a custom differentiable trajectory optimizer as a layer in neural networks, allowing us to update behavioural inputs by considering the optimizer's feedback. Moreover, our end-to-end approach also ensures that the learned behavioural inputs aid the convergence of the optimizer. We improve the state-of-the-art in the following aspects. First, we show that learned behavioural inputs substantially decrease collision rate while improving driving efficiency over handcrafted approaches. Second, our approach outperforms model predictive control methods based on sampling-based optimization.