BYD plans to incorporate its advanced driver-assistance system (ADAS), comparable to Tesla's Autopilot, into all its vehicle models. This technology, developed in-house and not reliant on third-party systems like Nvidia's, will be offered free of charge to customers. BYD emphasizes its self-sufficiency in developing this system, claiming it offers better integration and cost-effectiveness. The rollout will begin with the upcoming Seagull model, followed by other vehicles in the lineup throughout the year.
Waymo, Alphabet's self-driving unit, plans to expand its autonomous vehicle testing to over ten new US cities. Focusing on trucking and delivery services, Waymo will leverage its existing experience in Phoenix and San Francisco to gather data and refine its technology in diverse environments. This expansion aims to bolster the development and eventual commercial deployment of their autonomous driving systems for both passenger and freight transport.
HN commenters are generally skeptical of Waymo's expansion plans. Several point out that Waymo's current operational areas are geographically limited and relatively simple to navigate compared to more complex urban environments. Some question the viability of truly driverless technology in the near future, citing the ongoing need for human intervention and the difficulty of handling unpredictable situations. Others express concern about the safety implications of widespread autonomous vehicle deployment, particularly in densely populated areas. There's also discussion of the regulatory hurdles and public acceptance challenges that Waymo and other autonomous vehicle companies face. Finally, some commenters suggest Waymo's announcement is primarily a PR move designed to attract investment and maintain public interest.
This paper introduces a novel method for 3D scene reconstruction from images captured in adverse weather conditions like fog, rain, and snow. The approach leverages Gaussian splatting, a recent technique for representing scenes as collections of small, oriented Gaussian ellipsoids. By adapting the Gaussian splatting framework to incorporate weather effects, specifically by modeling attenuation and scattering, the method is able to reconstruct accurate 3D scenes even from degraded input images. The authors demonstrate superior performance compared to existing methods on both synthetic and real-world datasets, showing robust reconstructions in challenging visibility conditions. This improved robustness is attributed to the inherent smoothness of the Gaussian splatting representation and its ability to effectively handle noisy and incomplete data.
Hacker News users discussed the robustness of the Gaussian Splatting method for 3D scene reconstruction presented in the linked paper, particularly its effectiveness in challenging weather like fog and snow. Some commenters questioned the practical applicability due to computational cost and the potential need for specialized hardware. Others highlighted the impressive visual results and the potential for applications in autonomous driving and robotics. The reliance on LiDAR data was also discussed, with some noting its limitations in certain adverse weather conditions, potentially hindering the proposed method's overall robustness. A few commenters pointed out the novelty of the approach and its potential to improve upon existing methods that struggle with poor visibility. There was also brief mention of the challenges of accurately modelling dynamic weather phenomena in these reconstructions.
Self-driving buses, operating in simpler, more controlled environments than robotaxis, are emerging as a potentially faster route to widespread autonomous vehicle adoption. These buses can navigate fixed routes with fewer unpredictable variables, making them easier to deploy and potentially build public trust in autonomous technology. While challenges like complex intersections and pedestrian interactions remain, successful pilot programs suggest that autonomous buses could not only improve public transit but also pave the way for wider acceptance and eventual expansion of self-driving technology to personal vehicles.
HN commenters are generally skeptical of the claims made in the article about the potential of autonomous buses. Several point out the limitations of current self-driving technology, particularly in complex environments and unpredictable weather. Some highlight the "last mile" problem and doubt that these buses offer a significant advantage over existing public transit. Others question the economic viability, suggesting the cost and maintenance of these specialized vehicles might outweigh the benefits. A few commenters bring up safety concerns and the potential for accidents, referencing previous incidents involving autonomous vehicles. There's also discussion of the regulatory hurdles and public acceptance challenges that need to be overcome. While some express a degree of optimism, the overall sentiment appears to be cautious pessimism about the near-term impact of autonomous buses.
Summary of Comments ( 13 )
https://news.ycombinator.com/item?id=43018989
Hacker News commenters are skeptical of BYD's claim to offer "Tesla-like" self-driving tech for free. Several point out that "free" likely means bundled into the car price, not actually gratis. Others question the capabilities of the system, doubting it's truly comparable to Tesla's Autopilot or Full Self-Driving, citing the lack of detail provided by BYD. Some express concern over the potential safety implications of offering advanced driver-assistance systems without proper explanation and consumer education. A few commenters note BYD's vertical integration, suggesting they might be able to offer the technology at a lower cost than competitors. Overall, the sentiment is one of cautious disbelief, awaiting more concrete information from BYD.
The Hacker News post "BYD to offer Tesla-like self-driving tech in all models for free" has generated a number of comments discussing the announcement. Many express skepticism about BYD's claim of offering "Tesla-like" self-driving, particularly given the "for free" assertion. Several commenters point out that features like lane keeping and adaptive cruise control, while helpful, are not equivalent to the full self-driving capabilities Tesla advertises (and even those are not yet fully autonomous).
Some users highlight the difference between assisted driving features and true self-driving, suggesting that BYD's offering likely falls into the former category. The idea of providing such features "for free" is also debated, with some suggesting that the cost is simply built into the vehicle price. Others speculate that BYD might be using this as a marketing tactic to compete with Tesla, potentially offering a basic package of driver-assistance features as a standard inclusion.
A few comments delve into the complexities of self-driving technology, mentioning the hardware requirements (like sensors and processors) and the ongoing development of software algorithms. Some express doubt about BYD's ability to deliver a comparable system to Tesla's, especially given the rapid pace of innovation in the autonomous driving field.
The discussion also touches on the regulatory landscape for self-driving technology, with some commenters pointing out the challenges and uncertainties surrounding the approval and deployment of fully autonomous vehicles. One comment suggests that BYD's strategy could be to collect driving data from its vehicles to improve its self-driving system, similar to Tesla's approach.
Overall, the comments reflect a cautious attitude towards BYD's announcement, with many users questioning the scope and true nature of the "free" self-driving technology being offered. The prevailing sentiment seems to be one of "wait and see" until more details about BYD's system are revealed. There's a clear distinction drawn between the more common driver-assist features and true Level 5 autonomy, and most commenters believe BYD is offering the former, not the latter.